Decision Tree & Dialog Systems 2017


Notes:

A decision tree is a tree-like graph or model of decisions and their possible consequences.

  • Adaboost decision tree
  • Annotated decision tree
  • Applied decision tree
  • Binary decision tree
  • Boosted decision tree
  • Branching decision tree
  • Complex decision tree
  • Complicated decision tree
  • Contextual decision tree
  • Data driven decision tree
  • Decision analysis tool
  • Decision tree algorithm
  • Decision tree classifier
  • Decision tree clustering
  • Decision tree flow
  • Decision tree learner
  • Decision tree learning
  • Decision tree learning algorithm
  • Decision tree model
  • Decision tree-based estimation
  • Dialog decision tree
  • Enhanced decision tree
  • Factorized decision tree
  • Fixed decision tree
  • Fuzzy decision tree
  • Handcrafted decision tree
  • Hierarchical binary decision tree
  • KALDI toolkit decision tree
  • Learned decision tree
  • Meta decision tree
  • OCC decision tree
  • Optimal decision tree
  • Part-of-speech tagging using decision tree
  • Phonetic decision tree
  • Pictorial decision tree
  • Probabilistic decision tree
  • Prosodic decision tree
  • Trained decision tree models

Wikipedia:

References:

See also:

100 Best Decision Tree VideosKaldi ASRRandom Forest & Dialog Systems


Spoken language understanding for a nutrition dialogue system
M Korpusik, J Glass – IEEE/ACM Transactions on Audio …, 2017 – ieeexplore.ieee.org
… KORPUSIK AND GLASS: SPOKEN LANGUAGE UNDERSTANDING FOR A NUTRITION DIALOGUE SYSTEM … We explored three different classifiers, using the Scikit-learn toolkit’s implementation for Python [71]: a random forest (ie, a collection of decision tree classifiers trained …

Scaling up deep reinforcement learning for multi-domain dialogue systems
H Cuayáhuitl, S Yu, A Williamson… – Neural Networks (IJCNN …, 2017 – ieeexplore.ieee.org
… is still an open and interesting problem in artificial intelligence. The dialogue system proposed by [14] used a distributed architecture of domain experts modulated by a domain selector. The latter used a decision tree with classification errors over 20% in 5 domains …

Deep reinforcement learning: An overview
Y Li – arXiv preprint arXiv:1701.07274, 2017 – arxiv.org
… imperfect information games, in Section 11; AlphaGo in Section 12; robotics in Section 13; spoken dialogue systems (aka chatbot … For many machine learning algorithms, eg, linear regression, logistic regression, support vector machines (SVMs), decision trees, and boosting, we …

The technology behind personal digital assistants: an overview of the system architecture and key components
R Sarikaya – IEEE Signal Processing Magazine, 2017 – ieeexplore.ieee.org
… searches), which are captured in the history variable h in (1). This is used to model whether a specific user u will like the specific sug- gested entity .e Standard machine-learning techniques, such as maximum entropy models [35], gradient boosted decision trees [55], and deep …

Increasing Recall of Lengthening Detection via Semi-Automatic Classification
S Betz, J Voße, S Zarrieß… – Proceedings of …, 2017 – pub.uni-bielefeld.de
… It is possible to train a decision tree clas- sifier on the resulting data set, that reflects the human classifica- tion into disfluent and … Lengthening is a subtle phenomenon in speech that is interest- ing for speech synthesis in incremental dialogue systems, be- cause it is difficult to …

Reducing errors in object-fetching interactions through social feedback
D Whitney, E Rosen, J MacGlashan… – … (ICRA), 2017 IEEE …, 2017 – ieeexplore.ieee.org
… Williams and Young [24] casted a spoken dialogue system as a POMDP … Sparse sampling finds an approximate solution to the MDP by constructing a probabilistic decision tree of a finite depth d, where each node is a state-action pair, and chooses the action whose branch has …

An automatic procedure for generating datasets for conversational recommender systems
A Suglia, C Greco, P Basile, G Semeraro… – Proceedings of Dynamic …, 2017 – ceur-ws.org
… For this reason, synthetic dialogue datasets can be ex- tremely useful in order to bootstrap effective dialogue systems able to support a goal-oriented … Given a user u and his/her set of binary preferences, we trained a decision tree from the user u preferences expressed towards …

Ava: From Data to Insights Through Conversations.
RJL John, N Potti, JM Patel – CIDR, 2017 – pdfs.semanticscholar.org
… of the workflow. Each individual task in the work- flow (eg, “Train a decision tree model with the given set of hyper-parameters.”) maps to a short code sequence specific to the underlying library or platform in use. By maintain …

Explanation and justification in machine learning: A survey
O Biran, C Cotton – IJCAI-17 Workshop on Explainable AI (XAI), 2017 – intelligentrobots.org
… in context-aware applications that provides eight types of explanation for four of the most common model types (rules, decision trees, na?ve Bayes … sufficient for tasks such as picking the next course in a college curriculum;[Dodson et al., 2011] propose a dialog system, instead of …

Question selection based on expected utility to acquire information through dialogue
K Komatani, T Otsuka, S Sato, M Nakano – Dialogues with Social Robots, 2017 – Springer
… As future work, we will implement a dialogue system that incorporates the proposed method and conduct a user study to investigate … 124 (2014)Google Scholar. 6. Takahashi, Y., Dohsaka, K., Aikawa, K.: An efficient dialogue control method using decision tree-based estimation …

Words matter: automatic detection of teacher questions in live classroom discourse using linguistics, acoustics, and context
PJ Donnelly, N Blanchard, AM Olney, S Kelly… – Proceedings of the …, 2017 – dl.acm.org
… Vietnamese [34, 44]. Another study used prosodic features and a decision tree to detect questions from a dataset of Arabic language audio lectures containing an equal number of questions and statements [21]. Although the …

Evaluating Quality of Chatbots and Intelligent Conversational Agents
NM Radziwill, MC Benton – arXiv preprint arXiv:1704.04579, 2017 – arxiv.org
… Interactive Voice Response (IVR) systems (eg “Press or Say 1 for English”) are also dialog systems, but are not usually considered conversational agents since they implement decision trees. (McTear et al., 2016) These terms are related to each other in Figure 2. Page 4 …

A conversational dialogue manager for the humanoid robot erica
P Milhorat, D Lala, K Inoue, T Zhao… – Proceedings of …, 2017 – sap.ist.i.kyoto-u.ac.jp
… The key is the knowledge that “pizza” is the most relevant word in the previous utterance. This has also been used in previous robot dialogue systems [19]. We define four cases for replying to a statement as shown in Fig … Fig. 3 Decision tree for statement-response …

A roadmap for natural language processing research in information systems
D Liu, Y Li, MA Thomas – … of the 50th …, 2017 – hl-128-171-57-22.library.manoa …
… the refinement and application of NLP techniques to solve real-world problems [3], such as creating spoken dialogue systems [4], speech-to … algorithms that have been applied in NLP research include genetic algorithm (GA) [10], Naive Bayes [11], decision tree (DT), support …

Attentive listening system with backchanneling, response generation and flexible turn-taking
D Lala, P Milhorat, K Inoue, M Ishida… – Proceedings of the 18th …, 2017 – aclweb.org
… The model was trained with utterances from users interacting with two different dialogue systems. This corpus was then annotated to identify the fo- cus phrases of sentences. We use a decision tree in Figure 2 to decide from one of four response types …

Rationalization: A Neural Machine Translation Approach to Generating Natural Language Explanations
B Harrison, U Ehsan, MO Riedl – arXiv preprint arXiv:1702.07826, 2017 – arxiv.org
… to understand the model’s de- cision making process (in the case of rule based approaches such as decision trees) or examine … Encoder-decoder networks, which have primarily been used in machine translation and dialogue systems, are a generative architecture comprised of …

Phoneme Set Design Based on Integrated Acoustic and Linguistic Features for Second Language Speech Recognition
X Wang, T Kato, S Yamamoto – IEICE TRANSACTIONS on …, 2017 – search.ieice.org
… tions, and substitutions of phonemes or incorrect gram- mar [7]. More problematic is when non-native pronuncia- tions become an issue for spoken dialogue systems that tar … We also proposed a reduced phoneme set (RPS) created with a phonetic decision tree (PDT) method …

Reinforcement Learning Based Argument Component Detection
Y Gao, H Wang, C Zhang, W Wang – arXiv preprint arXiv:1702.06239, 2017 – arxiv.org
… appropriate SL-based classifiers. Widely used fea- tures include structural, lexical, syntactic and contextual fea- tures, and popular classifiers include SVM, naive Bayes, decision tree and random forest. For well-structured doc …

Sentence Selection Based on Extended Entropy Using Phonetic and Prosodic Contexts for Statistical Parametric Speech Synthesis
T Nose, Y Arao, T Kobayashi… – … /ACM Transactions on …, 2017 – ieeexplore.ieee.org
… A. Japanese Corpus Our main target application is a Japanese spoken dialogue system in which a human-like virtual actor responds to a user … of contexts in HMM-based speech synthesis because similar contexts are tied in the model training using decision-tree-based context …

An automatic classifier of emotions built from entropy of noise
J Ferreira, S Brás, CF Silva, SC Soares – Psychophysiology, 2017 – Wiley Online Library
… The goal of this study was to evaluate if the ECG noise allows for the classification of emotions, while using its entropy as an input in a decision tree classifier … In this study, we implemented a decision tree to categorize each emotion …

Shadowing synthesized speech–segmental analysis of phonetic convergence
I Gessinger, E Raveh, S Le Maguer… – Proc. Interspeech …, 2017 – coli.uni-saarland.de
… As spoken dialogue systems are being developed with the goal to eventually emulate natural dialogue situations, the implementation of convergence … The descriptive features and ques- tion sets used to build the decision tree followed the standard English set proposed in [17 …

I Can Parse You: Grammars for Dialogs
M Hirzel, L Mandel, A Shinnar, J Siméon… – LIPIcs-Leibniz …, 2017 – drops.dagstuhl.de
… Recently, human-computer dialog systems, also known as chat bots or virtual agents, received much renewed attention [14] … Diagnosis flow pattern Ask the human diagnostic questions following a decision tree to reach a leaf with a classification …

Predicting head pose in dyadic conversation
D Greenwood, S Laycock, I Matthews – International Conference on …, 2017 – Springer
… Nishimura et al. [26] presented a decision tree model driven by prosodic audio features … Nishimura, R., Kitaoka, N., Nakagawa, S.: A spoken dialog system for chat-like conversations considering response timing. In: International Conference on Text, Speech and Dialogue. pp …

Planning for persuasion
E Black, AJ Coles, C Hampson – Proceedings of the 16th Conference on …, 2017 – dl.acm.org
… [36], respectively, employ mixed observability Markov decision processes [32], partially observable Markov deci- sion processes [28], decision trees, and a … Caminada [10] presents an argument dialogue system that can be used to explain why an argument is justified under the …

A Data-Driven Approach to Dialog Structure Modeling
D Griol, A Sanchis, JM Molina – … Joint Conference SOCO’17-CISIS’17 …, 2017 – Springer
… The C4.5 decision tree learning algorithm has been used to learn this classification model, using the Weka machine learning software for … We have applied our proposal to the problem solving domain of a practical spoken dialog system, which acts as a customer support service …

Towards a Response Selection System for Spoken Requests in a Physical Domain
A Partovi, I Zukerman, Q Tran – pdfs.semanticscholar.org
… A combination of deep learning and reinforcement learning has been used in end-to-end dialogue systems that query a … Response Classification We experimented with several classification algorithms, in- cluding Na?ve Bayes, Support Vector Machines, Decision Trees (DT) and …

Towards an Argumentative Dialogue System
N Rach, W Minker, S Ultes – 2017 – cmna.csc.liv.ac.uk
… 2017. Strategic Sequences of Arguments for Persuasion Using Decision Trees. In Proceedings of the AAAI Conference on Arti cial Intelligence. AAAI Press … Page 3. Towards an Argumentative Dialogue System CMNA’17, June 16, 2017, London, UK [7] Henry Prakken. 2000 …

Detecting Spoken Corrections through Decision Tree Methods
GA Levow – cs.uchicago.edu
… only decision—tree model for dis?uency detec— tion. In Eurospeech ’97. Swerts, M., and Ostendorf. M. 1995. Discourse prosody in human—machine interactions. In Proceed- ings of the ECSA Tutorial and Research Workshop on Spoken Dialog Systems – Theories and …

A “small-data”-driven approach to dialogue systems for natural language human computer interaction
T Boros, SD Dumitrescu – Speech Technology and Human …, 2017 – ieeexplore.ieee.org
… A scenario is the equivalent of a frame in a in frame-based dialogue system, but by default we don’t log any … task may seem trivial at first, and easily solvable by employing any classifier (ie Conditional Random Fields, Support Vector Machines, Decision Trees, Neural Networks …

Towards End-to-End Modeling of Spoken Language Understanding in a Cloud-based Spoken Dialog System
Y Qian, R Ubale, V Ramanaryanan… – Proc. SEMDIAL 2017 …, 2017 – vikramr.com
… paper proposes an ASR- free, end-to-end (E2E) modeling approach to SLU for a cloud-based, modular spoken dialog system (SDS … NLU system performs multi-class classifica- tion of Bag of Words features extracted from the recognized hypotheses using decision tree classifier …

User-Adaptive A Posteriori Restoration for Incorrectly Segmented Utterances in Spoken Dialogue Systems
K Komatani, N Hotta, S Sato… – Dialogue & Discourse, 2017 – dad.uni-bielefeld.de
… results show that the proposed user adaptation approach applied to two restoration classification methods, thresholding and decision trees, improves classification accuracies by 3.0% and 7.4%, respectively, in cross validation. Keywords: spoken dialogue system, turn taking …

Selecting type of response for chat-like spoken dialogue systems based on acoustic features of user utterances
K Ohta, R Marumoto, R Nishimura… – Asia-Pacific Signal and …, 2017 – ieeexplore.ieee.org
… As examples of methods which select response types for spoken dialogue systems using acoustic features of user speech, Osuga et al … Kitaoka et al. [8] used decision trees to determine system timing for back-channel responses and turn- taking …

A study of fuzzy logic ensemble system performance on face recognition problem
A Polyakova, L Lipinskiy – IOP Conference Series: Materials …, 2017 – iopscience.iop.org
… The ensemble consists of several data mining algorithms: artificial neural network, support vector machine and decision trees … 3. Face recognition problem The automated human-machine system, working in the dialog mode is called a dialogue system …

Automated Speaker Recognition Methods: A Critical Review
SA Imam, P Bansal – pdfs.semanticscholar.org
… This research shall allow making spoken dialogue systems more intelligent in the future … conditions. The keynote idea of this approach is to 1) use a decision tree to hierarchically partition the whole population into blocks of small size, and determine …

Cognitive-affective dialog generation. integrating GOAL with dialog management
SN Conde Camacho – 2017 – pequod.det.uvigo.es
… It is driven by a set of interpretation rules that match the surface speech acts and Figure 2: Overview of the Spoken Dialog System proposed in [5] … This kind of architecture where activity or decision trees are present may not be the best choice …

Bootstrapping Chatbots for Novel Domains
P Babkin, MFM Chowdhury, A Gliozzo… – Workshop at NIPS on …, 2017 – hirzels.com
… These include sentence similarity estimation in the embedding space and decision tree learner-based feature selection leveraging structural regularities in API … While the resulting dialogue system is able to classify user utterances with reasonable accuracy, it only understands a …

Assistive and Adaptive Dialog Management
F Nielsen, W Minker – Companion Technology, 2017 – Springer
… capabilities was a cognitive knowledge-based technical system, which extends the architectures of classic unimodal (eg spoken dialog systems) or multimodal dialog systems … On the other hand a planner [13] is integrated to generate from a POMDP a decision tree …

Artificial intelligence in e-learning
HA Harouni, E Hachem, C Ziti – Shaping the Future of ICT: Trends …, 2017 – books.google.com
… 1 The Predictive Model Page 172. 6.7. 2 Exploring Data and Weka 6.7. 2.1 Logistic Regression 6.7. 2.2 Decision Tree Algorithm J48 6.7. 2.3 IBk 6.7 … Take dialogue systems, for example, which determine the emotional state of the user using a dialogic strategy …

Agent-Aware Dropout DQN for Safe and Efficient On-line Dialogue Policy Learning
L Chen, X Zhou, C Chang, R Yang, K Yu – Proceedings of the 2017 …, 2017 – aclweb.org
… Nowadays rule-based policy is popular in com- mercial dialogue systems … His knowledge of task domain and busi- ness rules is encoded in the rules. There are many methods to represent the decision rules, eg propositional logic, first-order logic, decision tree …

In-the-wild chatbot corpus: from opinion analysis to interaction problem detection
I Maslowski, D Lagarde, C Clavel – pdfs.semanticscholar.org
… Springer, 2013, pp. 83–95. [8] J. Liscombe, G. Riccardi, and D. Hakkani-Tür, “Using context to improve emotion detection in spoken dialog systems,” in Ninth European Conference on … [12] H. Schmid, “Probabilistic part-of-speech tagging using decision trees,” in Proceedings of …

A Benchmarking Environment for Reinforcement Learning Based Task Oriented Dialogue Management
I Casanueva, P Budzianowski, PH Su, N Mrkši?… – arXiv preprint arXiv …, 2017 – arxiv.org
… Under a speech-driven scenario, Spoken Dialogue Systems (SDSs) are typically based on a modular architecture (Fig … Traditional approaches have been mostly based on handcrafted decision trees covering all possible dialogues outcomes …

Speech recognition in a dialog system: from conventional to deep processing
A Becerra, JI de la Rosa, E González – Multimedia Tools and Applications, 2017 – Springer
Multimed Tools Appl DOI 10.1007/s11042-017-5160-5 Speech recognition in a dialog system: from conventional to deep processing … Keywords Speech recognition · Neural networks · Gaussian mixture models · Hidden Markov models · Deep learning · Spoken dialog system …

Using Vision and Speech Features for Automated Prediction of Performance Metrics in Multimodal Dialogs
V Ramanarayanan, P Lange, K Evanini… – ETS Research …, 2017 – Wiley Online Library
… While such an endeavor is crucial and relevant during the process of bootstrapping a dialog system for a new domain or … to automatically predict caller experience in interactive voice response systems using primarily log information and a decision tree-based classification …

Extrinsic Versus Intrinsic Evaluation of Natural Language Generation for Spoken Dialogue Systems and Social Robotics
H Hastie, H Cuayáhuitl, N Dethlefs, S Keizer… – Dialogues with Social …, 2017 – Springer
… P., Vanrompay, Y., Villazon-Terrazas, B.: Demonstration of the PARLANCE system: a data-driven incremental, spoken dialogue system for interactive … C., Gaši?, M., Henderson, M., Kim, D., Young, SJ: Dialogue context sensitive speech synthesis using factorized decision trees …

Prediction of Probability of Crying of a Child and System Formation for Cry Detection and Financial Viability of the System
G Joshi, C Dandvate, H Tiwari… – Vision, Image and …, 2017 – ieeexplore.ieee.org
… decision tree is fast but less accurate … infants(1987) [2] Y Wang, IH Witten : Induction of model trees for predicting continuous classes (1996) [3] M Walker, I Langkilde, J Wright, A Gorin : Learning to predict problematic situations in a spoken dialogue system: experiments with …

Hyperarticulation of Corrections in Multilingual Dialogue Systems
I Kraljevski, D Hirschfeld – Proc. Interspeech 2017, 2017 – researchgate.net
… dialogue acts in general was investigated in [6]. In [7] the duration, pause, and pitch features were employed to train a decision tree classifier, which was … The objective is to assess the effort for adaptation of a multilingual dialogue system from the aspect of recovery strategies …

A Hybrid Language Understanding Approach for Robust Selection of Tutoring Goals
R Srivastava, K VanLehn – cs.cmu.edu
… We computed average per essay performance over 25 trials of randomly selecting essays covering 10% of the corpus, training the decision tree using ID3 on the rest, and then testing the … Pedagogical content knowledge in a tutorial dialogue system to support self-explanation …

Automatic Phonetic Segmentation Using the Kaldi Toolkit
J Matoušek, M Klíma – International Conference on Text, Speech, and …, 2017 – Springer
… Thus, decision trees make the modeling more robust. The decision trees are typically built using questions on the immediate phonetic context of each phone model … Plátek, O., Jur?í?ek, F.: Integration of an on-line Kaldi speech recogniser to the Alex dialogue systems framework …

Studying Neurodegeneration With Automated Linguistic Analysis Of Speech Data
EA Korcovelos, KC Fraser, J Meltzer… – … & Dementia: The …, 2017 – aanddjournal.net
… Recently, computer programs based on the statistics of human dialogue have been shown to reduce the cost of hand-crafting complex dialogue systems … ST). Re- sults: Our decision tree model is able to classify CT versus ST+PPA+MCI with 76.1% accuracy …

Using Past Speaker Behavior to Better Predict Turn Transitions
M Tomer – 2017 – digitalcommons.ohsu.edu
… regulating turn allocation. This in turn will help guide us in how to implement such mechanisms in spoken dialogue systems. 2.1 Human-Human Conversations … acts to predict turn transitions. They trained decision tree models using the switchboard data. As …

Attention level approximation of a conversation in human-robot vocal interaction using prosodic features of speech
SD Wickramaratne… – Engineering Research …, 2017 – ieeexplore.ieee.org
… Emotional classification are based on methods such as fuzzy rules,decision trees,state vector machines and Hidden Markov Models [13]–[15 … APPROXIMATION OF ATTENTION LEVEL A. Rules for the Dialog System The characteristics of the human-robot dialog system is based …

Dialogue Intent Classification with Long Short-Term Memory Networks
L Meng, M Huang – National CCF Conference on Natural Language …, 2017 – Springer
… 28 (2006)Google Scholar. 6. Ali, SA, Sulaiman, N., Mustapha, A., Mustapha, N.: Improving accuracy of intention-based response classification using decision tree … T., Nishimoto, T., Araki, M.: A rule based approach to extraction of topics and dialog acts in a spoken dialog system …

A Proposed Model for a Web-Based Academic Advising System
E Afify, M Nasr – International Journal of Advanced Networking …, 2017 – search.proquest.com
… The phrases and advising information have been encoded using Artificial Intelligence Markup Language (AIML) and the dialog system has been … that models student advising as a search problem, whereby the search space is represented by a decision tree that embeds virtually …

Towards Multimodal Coreference Resolution for Exploratory Data Visualization Dialogue: Context-Based Annotation and Gesture Identification
A Kumar, B Di Eugenio, J Aurisano, A Johnson… – SEMDIAL 2017 SaarDial – evl.uic.edu
… humans interact with complex data and visualizations thereof in order to make discoveries; and use our findings to develop a dialogue system for exploring … Classifier Accuracy Support Vector Machine 74% Decision Tree 74% Random Forest 73% Multinomial Naive Bayes 64 …

19 Speech Synthesis: State of the Art and Challenges for the Future
K Georgila – Social Signal Processing, 2017 – books.google.com
… it can be used as an aid to people with disabilities (see Challenges for the Future), for generating the output of spoken dialogue systems (Lemon et al … There is also unit selection based on clustering of units of the same phoneme class using a decision tree (Black & Taylor, 1997) …

e-QRAQ: A Multi-turn Reasoning Dataset and Simulator with Explanations
C Rosenbaum, T Gao, T Klinger – arXiv preprint arXiv:1708.01776, 2017 – arxiv.org
… Other work has stud- ied the interpretability of traditional machine learning algo- rithms, such as decision trees (Hara & Hayashi, June 2016), graphical models (Kim et al., 2015), and learned rule-based … Evaluating prerequisite qualities for learning end-to-end dialog systems …

Online POMDP Algorithms for Very Large Observation Spaces
WS Lee – 2017 – dtic.mil
… tool that has been shown to be useful in various problems of planning and control under uncertainty, including dialog systems, assistive technologies, and … a road network with some roads that may be blocked, as well as the reduction from optimal decision tree (ODT) problem …

Literature Survey
R Chakraborty, M Pandharipande… – Analyzing Emotion in …, 2017 – Springer
… an interesting study reported in [7], authors experimented with both elicited speech and speech acquired through WoZ scenario, where users believe that they are in conversation with dialogue system … Results were compared for neural network , SVM , KNN, and decision trees …

Sarcasm Identification on Twitter: A Machine Learning Approach
A Onan – Computer Science On-line Conference, 2017 – Springer
… are simplified, while obtaining promising predictive performance comparable to other conventional supervised learning algorithms, such as decision trees and artificial … Tepperman, J., Traum, DR, Narayanan, S.: “yeah right”: sarcasm recognition for spoken dialogue systems …

Design and Evaluation Methods, Tools and Practices
K Angkananon, M Wald, P Ploadaksorn, TP Anjos… – pdfs.semanticscholar.org
… 450 Junko Itou, Rina Tanaka, and Jun Munemori Collection of Example Sentences for Non-task-Oriented Dialog Using a Spoken Dialog System and Comparison with Hand-Crafted DB . . . . 458 Yukiko Kageyama, Yuya Chiba, Takashi Nose, and Akinori Ito …

A Proposal to Integrate Conversational Interfaces in Mobile Learning Applications
D Griol, A Sanchis, JM Molina – … Joint Conference SOCO’17-CISIS’17 …, 2017 – Springer
… N.: On predicting learning styles in conversational intelligent tutoring systems using fuzzy decision trees. Int. J. Hum.-Comput. Stud. 97, 98–115 (2017)CrossRefGoogle Scholar. 3. Dowding, J., Clancey, W., Graham, J.: Are you talking to me? Dialogue systems supporting mixed …

Subject-independent emotion recognition based on physiological signals: a three-stage decision method
J Chen, B Hu, Y Wang, P Moore… – BMC medical …, 2017 – bmcmedinformdecismak …
Skip to content Advertisement …

Analysis of problem tokens to rank factors impacting quality in VoIP applications
J Gupchup, Y Hosseinkashi, M Ellis… – Quality of Multimedia …, 2017 – ieeexplore.ieee.org
… The decision tree approach is highly suited for troubleshooting but it does not provide a breakdown of the top-level metric into its components in an uncorrelated … [6] ITU-T, “Subjective quality evaluation of telephone services based on spoken dialogue systems,” November 2003 …

Designing User Interfaces in Emotionally-Sensitive Applications
A Sutcliffe – IFIP Conference on Human-Computer Interaction, 2017 – Springer
… The OCC decision tree helps to identify potential emotions and their causes by asking questions about the source of the problem (agents … In: van Kuppevelt, J., Dybkjaer, L., Bernsen, NO (eds.) Natural, Intelligent and Effective Interaction with Multimodal Dialogue Systems …

A tool to design interactive characters based on embodied cognition
J Llobera, R Boulic – … on Computational Intelligence and AI in …, 2017 – ieeexplore.ieee.org
… There is a plethora of variations, but the essential idea is that an agent makes decisions based on decision trees, with simple rules (pass … of the modular organization of Skills and implement one or several Skills from an existing implementation of Spoken Dialog Systems (SDS) …

Emotion recognition on speech signals using machine learning
M Ghai, S Lal, S Duggal, S Manik – Big Data Analytics and …, 2017 – ieeexplore.ieee.org
… to these samples: By averaging the prediction values or by taking the majority vote from all the decision trees we predict … Alpkocak, “Emotion Classification of Audio Signals Using Ensemble of Support Vector Machines”, Perception in Multimodal Dialogue Systems Volume 5078 …

A Hybrid Architecture for Multi-Party Conversational Systems
MG de Bayser, P Cavalin, R Souza, A Braz… – arXiv preprint arXiv …, 2017 – arxiv.org
… Page 2. Turing’s test. Some of them have won prizes, some not [5]. Although in this paper we do not focus on creating a solution that is able to build conversational systems that pass the Turing’s test, we focus on Natural Dialogue Systems (NDS) …

Online End-of-Turn Detection from Speech based on Stacked Time-Asynchronous Sequential Networks
R Masumura, T Asami, H Masataki… – Proc …, 2017 – pdfs.semanticscholar.org
… This is because conventional discriminative modeling such as decision trees or support vector machines could not support variable-length features … 7. References [1] NG Ward and DD Vault, “Ten challenges in highly-interactive dialog systems,” AAAI Spring Symposium, Turn …

Multi-Task Deep Learning for User Intention Understanding in Speech Interaction Systems
Y An, Y Wang, H Meng – 2017 – aaai.org
… 2000) proposed to utilize acoustic cues such as F0 shape and duration to classify communicative inten- tions in dialog systems. (Matsubara et al. 2002) presented an example-based method for inferring speaker’s intention. (Irie et al. 2004) used a decision tree learning method …

Advances in Electronics, Communication and Computing: ETAEERE-2016
A Kalam, S Das, K Sharma – 2017 – books.google.com
… Benmoussa, A. Rhattoy, M. Lahmer and I. Chana Predictive Modeling of Students Performance Through the Enhanced Decision Tree … 613 Sandhyalaxmi G. Navada, Chandrashekara S. Adiga and Savitha G. Kini Spoken Dialog System in Bodo Language for …

Speech interface dialog with smart glasses
A Firouzian, P Pulli, M Pleva, J Juhar… – … (ICETA), 2017 15th …, 2017 – ieeexplore.ieee.org
… dialogue provides several items for selection. There are many studies arguing number of possible items to remember in voice dialogue system … Partitioned input message is designed to systematically categorized possible inputs from user, similar to a decision tree model …

Machine Learning: Adaptive Negotiation Agents in E-Commerce
D Pandey, RG Tiwari, P Kumar – pdfs.semanticscholar.org
… 2.1.6 Decision Trees A decision tree or a classification tree is a tree in which each non-leaf (internal) node is labelled with an input feature … Such an agent may basically consist of a dialog system, an avatar as well as expert system to provide specific expertise to the user …

Hierarchical Dialogue Management
F Giordaniello, T Voice, M Gaši? – pdfs.semanticscholar.org
… Page 6. Page 7. Abstract The dialogue management in a Spoken Dialogue System aims at learning a decision rule … Page 13. Background 2.1 Statistical Spoken Dialogue Systems A Statistical Spoken Dialogue System (SSDS) is an architecture composed by several …

From the lab to the real-world: An investigation on the influence of human movement on Emotion Recognition using physiological signals
Y Xu, I Hübener, AK Seipp, S Ohly… – … Workshops), 2017 IEEE …, 2017 – ieeexplore.ieee.org
… Our results show that the Decision Tree is the best classification algorithm … 530–537, 2007. [9] A. Haag, S. Goronzy, P. Schaich, and J. Williams, “Emotion recognition using bio-sensors: First steps towards an automatic system,” Affective Dialogue Systems, pp. 36–48, 2004 …

An open-ended computational construction grammar for Spanish verb conjugation
K Beuls – Constructions and Frames, 2017 – jbe-platform.com
… grammars that can be used in real-world applications, such as language tutoring systems (Beuls 2013) or dialogue systems, the original … A linguistically motivated decision tree designed by Rello & Basterrechea (2011) in the context of the development of the Onoma conjugator …

UE-HRI: a new dataset for the study of user engagement in spontaneous human-robot interactions
A Ben-Youssef, C Clavel, S Essid, M Bilac… – Proceedings of the 19th …, 2017 – dl.acm.org
… Ang et al. [1] use prosodic features, language modelling and speaking style to detect user frustration with a telephone-based dialog system interface. They show that a prosodic decision trees can predict whether an utterance is neutral or “annoyed or frustrated” …

Supporting collaboration with non-literate forest communities in the congo-basin
M Vitos, J Altenbuchner, M Stevens… – Proceedings of the …, 2017 – discovery.ucl.ac.uk
… When introducing Sapelli, and since pictorial decision trees play a central role in our work, we firstly engage the crowd in training exercises, where we introduce them to the pictorial icons, printed on large flashcards (Figure 3a) …

Gaze and filled pause detection for smooth human-robot conversations
M Bilac, M Chamoux, A Lim – Humanoid Robotics (Humanoids) …, 2017 – ieeexplore.ieee.org
… Thirdly, we present our HOMAGE turn-taking system that combines our filler detection method and human gaze information into the dialogue system. Finally, we present an experiment evaluating the system … We implemented these rules in our decision tree (see Figure 3) …

Automated Speech Recognition System–A Literature Review
M Manjutha, J Gracy, P Subashini… – COMPUTATIONAL … – researchgate.net
… Some of the major growing applications are Language Identification, Speech Enhancement, Spoken Dialog System, Speaker Recognition … Quantization, Feature Extraction, Dynamic Time Warping, Hidden Markov Models, Gaussian Mixture Model, Decision-tree based Clustering …

Toward Empathic Agents for Defusing Toxic Behaviors on Team Competition Games
K Watanabe, N Fukuta – … Applied Informatics (IIAI-AAI), 2017 6th …, 2017 – ieeexplore.ieee.org
… TABLE I COMPARISON RESULT OF CLASSIFICATION POSSIBILITY Classifier Precision Recall F-Measure Decision Tree 0.913 0.914 0.907 … H. Hastie, A. Deshmukh, and R. Aylett, “Towards a serious game playing empathic robotic tutorial dialogue system,” in Proceedings of …

HMM-Based Photo-Realistic Talking Face Synthesis Using Facial Expression Parameter Mapping with Deep Neural Networks
K Sato, T Nose, A Ito – Journal of Computer and Communications, 2017 – scirp.org
… A spoken dialogue system with facial information is richer than that with only speech, and it often gives friendlier impression to users … State-dependent model-parameter tying using context clustering with contextual decision trees is performed because the number of possible …

Continuous Learning as a Service for Conversational Virtual Agents
S Agarwal, S Atreja, G Dasgupta – International Conference on Service …, 2017 – Springer
… a result of massive training in relevant domains using technologies like machine learning, natural language processing, dialog decision tree flows etc … Particularly for dialog systems and conversation agents, [16, 19] exploited a combination of active and semi-supervised learning …

Remembering what you said: Semantic personalized memory for personal digital assistants
V Agarwal, OZ Khan, R Sarikaya – Acoustics, Speech and …, 2017 – ieeexplore.ieee.org
… We eval- uate the use of various learning algorithms (SVM, Logistic Regression and Gradient Boosted Decision Trees) … Referring entity expressions (descriptive, anaphoric as well as deitic) have been extensively studied in dialog systems [5, 6, 7, 8, 9]. The resolution of REs for …

A radial base neural network approach for emotion recognition in human speech
L Hussain, I Shafi, S Saeed, A Abbas, IA Awan… – IJCSNS, 2017 – paper.ijcsns.org
… Besides, there are some other emotion recognition systems to recognize real-life emotions such as dialogue systems, surveillance, tasks and media … Besides, SVM and decision tree classifiers are used to recognize human activities based on control parameters [8]. HCI is used …

Opinion Mining in Twitter: How to make use of Sarcasm to Enhance Sentiment Analysis: A
S Parveen, A Surnar, S Sonawane – ijarcet.org
… 2013] use Naive Bayes and decision trees for multiple … Association for Computational Linguistics [4] Joseph Tepperman, DR “Yeah right: sarcasm recognition for spoken dialogue systems”, In Proceedings of INTERSPEECH [5] CC Liebrecht, FK “The perfect solution for detecting …

Joint Learning of Dialog Act Segmentation and Recognition in Spoken Dialog Using Neural Networks
T Zhao, T Kawahara – Proceedings of the Eighth International Joint …, 2017 – aclweb.org
… Therefore DA segmentation becomes essential for spoken dialog systems … 2 Related Works In the task of DA recognition, Shriberg et al. (1998) applied decision tree using rich features and emphasized the importance of prosodic fea- tures. Stolcke et al …

Towards a continuous speech corpus for banking domain automatic speech recognition
G Suciu, ?A Toma… – Speech Technology and …, 2017 – ieeexplore.ieee.org
… Keywords—speech corpus; banking; dialogue system; automatic speech recognition … C. Grapheme to phoneme conversion For grapheme to phoneme conversion we applied a decision tree based classifier inspired by the work in [26] …

Addressing challenges in promoting healthy lifestyles: the al-chatbot approach
A Fadhil, S Gabrielli – Proceedings of the 11th EAI International …, 2017 – dl.acm.org
… This model outperforms fixed decision trees and can complete more complex tasks while reduce friction [8]. The idea with this model is to detect all parameters required to 1 https://dev. botframework.com/ 2 http://monkeylearn.com … “Anna: A Nutrition-Facts Dialogue System.”

Graph Databases for Designing High-Performance Speech Recognition Grammars
M Di Maro, M Valentino, A Riccio, A Origlia – IWCS 2017—12th …, 2017 – aclweb.org
… Ontology-based dialogue systems. In Proc. 3rd Workshop on Knowledge and reasoning in practical dialogue systems (IJCAI03), pp. 9–18. Citeseer … Schmid, H. (2013). Probabilistic part-of speech tagging using decision trees. In New methods in language processing, pp. 154 …

Improving Deep Neural Network Based Speech Synthesis through Contextual Feature Parametrization and Multi-Task Learning
Z Wen, K Li, Z Huang, CH Lee, J Tao – Journal of Signal Processing …, 2017 – Springer
… Most of these con- textual features are binary features suitable to construct the decision trees in the hidden Markov model (HMM)-based speech synthesis system [19], however they may be insuffi- cient to represent the DNN’s input …

Affective Valence Detection from EEG Signals Using Wrapper Methods
AR Hidalgo?Muñoz, MM López, IM Santos… – Emotion and Attention …, 2017 – intechopen.com
… Then, a classifier (a decision tree, C4.5 algorithm) was applied to the set of features to identify the affective state … The random forest is an ensemble of binary decision trees where the training is achieved by randomly selecting subsets of features …

Domain-Specific Utterance End-Point Detection for Speech Recognition
R Maas, A Rastrow, K Goehner, G Tiwari… – Proc. Interspeech …, 2017 – isca-speech.org
… [16] E. Shriberg, RA Bates, and A. Stolcke, “A prosody only decision-tree model for … [19] J. Edlund, M. Heldner, and J. Gustafson, “Utterance segmentation and turn-taking in spoken dialogue systems,” Sprachtechnologie, mobile Kommunikation und linguistische Ressourcen, pp …

BabelDr vs Google Translate: a user study at Geneva University Hospitals (HUG)
P Bouillon, J Gerlach, H Spechbach, N Tsourakis… – 2017 – archive-ouverte.unige.ch
… It allows medical professionals to perform a preliminary medical examination di- alogue, using a decision-tree method, to determine the nature of the patient’s problem and the appro- priate action to … A Scalable Architecture For Web Deployment of Spo- ken Dialogue Systems …

Dialect classification using vowel acoustic parameters
C Themistocleous – Speech Communication, 2017 – Elsevier
… processing applications, such as in speech-to-text systems, spoken document retrieval, spoken language translation, and in dialogue systems (see Li … C5.0 generates a decision tree and offers a ranking of features that can indicate the contribution of each acoustic feature in the …

Empirical methods for modelling persuadees in dialogical argumentation
A Hunter, S Polberg – Proceedings of the International Conference on …, 2017 – cs.ucl.ac.uk
Page 1. Empirical Methods for Modelling Persuadees in Dialogical Argumentation Anthony Hunter?, Sylwia Polberg? ? Department of Computer Science, University College London, London, United Kingdom Abstract—For …

to Playable Stories
ML Ryan – StoryWorlds: A – ctcs505.com
… The genres of playable stories include table-top role playing games (also known as Dungeons and Dragons), stories based on decision trees, hypertext fiction, simulation games (like The Sims), and interactive drama, a digital genre best described as an attempt to implement …

Dialogue Act Recognition for Conversational Agents
LE Hacquebord – 2017 – dspace.library.uu.nl
… 7 2.3 Dialogue System Architecture … Page 15. 3 Chapter 2 Background Information This chapter provides some background information on natural language processing (NLP) and dialogue systems that is necessary to understand the remaining parts of the thesis …

Affective prediction by collaborative chains in movie recommendation
Y Zheng – Proceedings of the International Conference on Web …, 2017 – dl.acm.org
… endEmo is independent. In this case, most of the classical classi cation algorithms can be adopted in the multi-class classi cation process, such as decision trees, random forest, support vector machines, and so forth. 4.2 Dependent …

Analyzing User Emotions via Physiology Signals
B Myroniv, CW Wu, Y Ren, A Christian, E Bajo… – ikelab.net
… KNN), J48 Decision Tree (abbr … [26] Andreas Haag, Silke Goronzy, Peter Schaich, Jason Williams,“Emotion Recognition Using Biosen- sors: First Steps towards an Automatic System,” Affective Dialogue Systems, Tutorial and Research Workshop, ADS, Kloster Isree, 2004 …

Dialogue Act Semantic Representation and Classification Using Recurrent Neural Networks
P Papalampidi, E Iosif, A Potamianos – SEMDIAL 2017 SaarDial, 2017 – academia.edu
… 1 Introduction Dialogue Act (DA) classification constitutes a ma- jor processing step in Spoken Dialogue Systems (SDS) assisting the understanding of … Hidden Markov Models (HMM)(Stolcke et al., 2000), feed-forward Neural Networks (Ji et al., 2016), Decision Trees (Ang et al …

Artificial Intelligence in Bio-Medical Domain
M Salman, AW Ahmed, OA Khan… – Artificial …, 2017 – pdfs.semanticscholar.org
… Demonstrator to AI research is that physicians and therefore the computer can interact in disrupted communication and dialogue, system ceaselessly being attentive of all the knowledge we are … Different algorithms and decision trees are also proposed for learning knowledge …

A review of Serbian parametric speech synthesis based on deep neural networks
T Deli?, M Se?ujski, S Suzi? – Telfor Journal, 2017 – scindeks.ceon.rs
… The research was conducted within the project “Development of Dialogue Systems for Serbian and Other South Slavic Languages” (TR32035 … This problem is solved using decision-tree-based clustering [10], which merges models in similar contexts and estimates joint …

Natural language inference over interaction space
Y Gong, H Luo, J Zhang – arXiv preprint arXiv:1709.04348, 2017 – arxiv.org
… et al., 2014), abstractive summa- rization(Rush et al., 2015), Reading Comprehension(Hermann et al., 2015), dialog system(Mei et al … Poten- tially all exiting approaches in machine learning, such as decision tree, support vector machine and neural network approach, can be …

Ensemble softmax regression model for speech emotion recognition
Y Sun, G Wen – Multimedia Tools and Applications, 2017 – Springer
… With the growth in the electronic and computer technologies, new spoken dialogue systems with emotion recognition capability are needed … For example, random forest and Adaboost- decision tree choose the strong classifiers as the base ones, but they have bad effect for …

Situation Understanding for Turn-Taking in Human-Robot Dialogue
???? – 2017 – ir.library.osaka-u.ac.jp
… Chapter 1 provides this study’s background, and introduces a new architec- ture of spoken dialogue systems for humanoid robots in public spaces. Chapter 2 Page 5. ii … a social channel (human-like utterances and motions). 1.2 Architecture of Spoken Dialogue Systems for …

Towards a theory of close analysis for dispute mediation discourse
M Janier, C Reed – Argumentation, 2017 – Springer
… Decision analysis systems allow for suppressing, or at least minimizing, numerous barriers to settlement. By their designing a decision tree, decision analysis tools transform the conflict into a logical structure from all the issues to all the possible solutions, and the ideal solution …

Arabic Speech Recognition Systems
HMM Eljagmani – 2017 – repository.lib.fit.edu
… 1996). 2-Sphinx 2: It is a high speed large vocabulary speech recognizer that was developed on the basis of Sphinx1 in 1922. It used in pronunciation learning systems, dialogue systems and interactive applications. Sphinx 2 introduced the design of PocketSphinx …

Speech emotion recognition with skew-robust neural networks
PY Shih, CP Chen, HM Wang – Acoustics, Speech and Signal …, 2017 – ieeexplore.ieee.org
… examples of applications, SER can be incorporated in automatic speech recognition sys- tems or spoken dialogue systems to improve … Carlos Busso, Sungbok Lee, and Shrikanth Narayanan, “Emotion recogni- tion using a hierarchical binary decision tree approach,” Speech …

Automatically Classifying User Engagement for Dynamic Multi-party Human–Robot Interaction
ME Foster, A Gaschler, M Giuliani – International Journal of Social …, 2017 – Springer
… IB1. A nearest-neighbour classifier that uses normalised Euclidean distance to find the closest training instance [2]. J48. Classifies instances using a pruned C4.5 decision tree [57]. JRip. Implements the RIPPER propositional rule learner [13]. LibSVM …

Complementing the Execution of AI Systems with Human Computation
E Kamar, L Manikonda – AAAI Workshop on …, 2017 – pdfs.semanticscholar.org
Page 1. Complementing the Execution of AI Systems with Human Computation Ece Kamar1, Lydia Manikonda*2 1 Microsoft Research, Redmond, WA 2 Arizona State University, Tempe, AZ eckamar@microsoft.com, lmanikonda@asu.edu Abstract …

Review on Multiple Classifier System in Pattern Recognition
VV Kamble, RD Kokate – International Conference on …, 2017 – pdfs.semanticscholar.org
… 3 hierarchical Emotion recognition 3 Chung-Hsien Wu and Wei-Bin Liang (2011)[4] corpora A, co rpora B MFCC 3 Meta decision Tree Emotion recognition … Enhancement of emotion detection in spoken dialogue systems by combining several information sources …

Enhancing Backchannel Prediction Using Word Embeddings
R Ruede, M Müller, S Stüker… – Proc. Interspeech …, 2017 – pdfs.semanticscholar.org
… [5] trained a decision tree with the C4.5 learn- ing algorithm to distinguish between BC responses, turn-taking, and turn-keeping without a BC … 20, no. 1, pp. 70–84, 2010. [5] M. Takeuchi, N. Kitaoka, and S. Nakagawa, “Timing detection for realtime dialog systems using prosodic …

Personalized question recommendation for English grammar learning
L Fang, LA Tuan, SC Hui, L Wu – Expert Systems – Wiley Online Library
By continuing to browse this site you agree to us using cookies as described in About Cookies. Remove maintenance message …

Big Five Personality Recognition from Multiple Text Genres
VG dos Santos, I Paraboni, BBC Silva – International Conference on Text …, 2017 – Springer
… All models use decision-tree induction with 10-fold cross-validation over the entire dataset … In: The Joint Annual Meeting of the 37th Interface Symposium and the CSNA (2005)Google Scholar. 3. Mairesse, F.: Learning to adapt in dialogue systems: data-driven models for …

Interactive Concept of Operations Narrative Simulators
AR Denham – 2017 – ntrs.nasa.gov
… A. Interactive Fiction Interactive fiction (IF), also known as text adventures or text games, is a dialog system contained within a text- based … Twine could be used to create branching decision trees for each scenario, with the scenario framework being at the top level, space markets …

Business Applications of Deep Learning
A Vieira – Ubiquitous Machine Learning and Its Applications, 2017 – books.google.com
… They lack the transparency and interpretability of other methods, like decision trees … Business Applications of Deep Learning 5.2. Chatbots Chatbots, also called Conversational Agents or Dialog Systems, are algorithms designed to have human level conversation capabilities …

An Adaptive Learning with Gamification & Conversational UIs: The Rise of CiboPoliBot
A Fadhil, A Villafiorita – Adjunct Publication of the 25th Conference on …, 2017 – dl.acm.org
… A work by Mazur et. al., [7] proposed a free talking dialogue system designed for tutoring English language … Figure 3: The CiboPoli High-level Architecture. 3.4 The CiboPoli Design The game consists of steps designed in a decision tree-like structure …

Leveraging Tokens in a Natural Language Query for NLIDB Systems
A Palakurthi – 2017 – pdfs.semanticscholar.org
… A dialogue system [18], [60], [25], [11], [41], [46], [28] is a system which interacts with humans in natural language, similar to the way in which humans interact with each other … Typically, a dialogue system consists of six components [4], which are as follows …

Advances in Electronics, Communication and Computing
A Kalam, S Das, K Sharma – Springer
… Benmoussa, A. Rhattoy, M. Lahmer and I. Chana Predictive Modeling of Students Performance Through the Enhanced Decision Tree … 613 Sandhyalaxmi G. Navada, Chandrashekara S. Adiga and Savitha G. Kini Spoken Dialog System in Bodo Language for …

Improving the understanding of spoken referring expressions through syntactic-semantic and contextual-phonetic error-correction
I Zukerman, A Partovi – Computer Speech & Language, 2017 – Elsevier
… For example, a research prototype of a spoken slot-filling dialogue system reported a Word Error Rate (WER) of 13.8% when … We experimented with Decision Trees (DT) (Quinlan, 1993), Naïve Bayes (NB) (Domingos and Pazzani, 1997), and Support Vector Machines (SVMs …

Lexical Acquisition through Implicit Confirmations over Multiple Dialogues
K Ono, R Takeda, E Nichols, M Nakano… – Proceedings of the 18th …, 2017 – aclweb.org
… 1 Introduction Much attention has recently been paid to non-task-oriented dialogue systems —or chat- oriented dialogue systems— both in research (Higashinakaetal., 2014; Yuetal., 2016) and in industry. In addition to pure …

Shallow PARsing and Knowledge extraction for Language Engineering
I Annex – cogsci.ed.ac.uk
… Speech dialogue systems will soon be in the position of providing services such as data base access via telephone … Black et al. (1992a) propose a general probabilistic parsing technique using decision trees to model arbitrary aspects of context and report an experiment with …

Random deep belief networks for recognizing emotions from speech signals
G Wen, H Li, J Huang, D Li, E Xun – Computational intelligence and …, 2017 – hindawi.com
… The neural network, decision tree, SVM, and KNN are combined [27] … 1537–1540, Dresden, Germany, 2015. T. Danisman and A. Alpkocak, “Emotion classification of audio signals using ensemble of support vector machines,” Perception in Multimodal Dialogue Systems, vol …

Natural Language Processing, Moving from Rules to Data
AH Dediu, JM Matos, C Martín-Vide – International Conference on Theory …, 2017 – Springer
During the last decade, we assist to a major change in the direction that theoretical models used in natural language processing follow. We are moving from rule-based systems to corpus-oriented paradi.

A User Perception–Based Approach to Create Smiling Embodied Conversational Agents
M Ochs, C Pelachaud, G Mckeown – ACM Transactions on Interactive …, 2017 – dl.acm.org
… [2010]. Based on this smile corpus and on a decision-tree classification technique, described in the next section, we have extracted the morphological and dynamic characteristics of the smile types that a virtual agent may express. 4.2 … Decision tree …

Evaluating LSTM Networks, HMM and WFST in Malay Part-of-Speech Tagging
TP Tan, B Ranaivo-Malançon… – Journal of …, 2017 – journal.utem.edu.my
… in modeling sequential data such as phoneme recognition, speech translation, language modeling, speech synthesis, chatbot-like dialog systems and others … On the other side, machine learning techniques have been tested such as decision trees [11], k-nearest neighbor [11 …

Natural Language Processing: State of The Art, Current Trends and Challenges
D Khurana, A Koli, K Khatter, S Singh – arXiv preprint arXiv:1708.05148, 2017 – arxiv.org
… Cohen 1996)[45], Naïve Bayes (Sahami et al., 1998 ;Androutsopoulos et al.,2000b ;Rennie .,2000)[46][47][48],Memory based Learning (Androutsopoulos et al.,2000b)[47], Support vector machines (Druker et al., 1999)[49], Decision Trees (Carreras and … 6.6 Dialogue System …

KIT-Conferences
MIAR Roedder – 2017 – isl.anthropomatik.kit.edu
… 04, 2017. Yeah, Right, Uh-Huh: A Deep Learning Backchannel Predictor, Robin Ruede, Markus Müller, Sebastian Stüker, Alex Waibel. International Workshop on Spoken Dialogue Systems Technology 2017, Farmington, Pennsylvania, USA. 6th – 9th June, 2017 …

Altruistic behaviours-based recommendation system of tourist information from smartphone application to SNS community
T Ichimura, T Uemoto… – International Journal of …, 2017 – inderscienceonline.com
… Page 7. 276 T. Ichimura et al. et al., 2012; Rauber et al., 2002) and the decision tree by C4.5 (Quinlan, 1996) by our developed smartphone application. The filtering rules are generated according to the acquired knowledge …

End-to-End Large Vocabulary Speech Recognition for the Serbian Language
B Popovi?, E Pakoci, D Pekar – International Conference on Speech and …, 2017 – Springer
… framework that discards most of the above mentioned elements, such as HMM-GMM state topologies, decision tree questions and … of Education, Science and Technological Development of the Republic of Serbia, within the project “Development of Dialogue Systems for Serbian …

Emotion Recognition from Speech
A Wendemuth, B Vlasenko, I Siegert, R Böck… – Companion …, 2017 – Springer
… Regarding static modeling, the list of possible classification techniques seems endless: multi-layer perceptrons or other types of neural networks, Bayes classifiers, Bayesian decision networks, random forests, Gaussian mixture models (GMMs), decision trees, k-nearest …

Empirical analysis of cyber-attacks to an indoor real time localization system for autonomous robots
ÁM Guerrero-Higueras, N DeCastro-García… – Computers & …, 2017 – Elsevier
… meaningful differences. Also, if more than one distribution is analyzed, it allows deciding which one is the best distribution in order to detect cyber-attacks. Fig. 5 shows the decision tree, considering the three distributions of beacons …

Dynamic Gesture Recognition for Social Robots
JC Castillo, D Cáceres-Domínguez… – … Conference on Social …, 2017 – Springer
… Random forest. 0.999. Decision tree. Neural network. 0.969. Neural network … Cybern. Syst. 42(4), 215–245 (2011)CrossRefGoogle Scholar. 4. Alonso-Martín, F., Castro-González, A., Luengo, F., Salichs, M.: Augmented robotics dialog system for enhancing human-robot interaction …

Real time speech emotion recognition using RGB image classification and transfer learning
MN Stolar, M Lech, RS Bolia… – Signal Processing and …, 2017 – ieeexplore.ieee.org
Page 1. Real Time Speech Emotion Recognition Using RGB Image Classification and Transfer Learning Melissa N. Stolar, Margaret Lech School of Engineering, RMIT University, Melbourne, Australia e-mail: {melissa.stolar, margaret.lech}@rmit.edu.au …

Preserving word-level emphasis in speech-to-speech translation
QT Do, T Toda, G Neubig, S Sakti… – … /ACM Transactions on …, 2017 – ieeexplore.ieee.org
… Yu et al. [3] proposed a method to model word-level emphasis in hidden Markov model (HMM)-based TTS using factorized decision trees, but there is no emphasis estimation or translation involved … Fig. 6. An example of a decision tree with emphasis questions …

Modeling Target-Side Inflection in Neural Machine Translation
A Tamchyna, MWD Marco, A Fraser – arXiv preprint arXiv:1707.06012, 2017 – arxiv.org
Page 1. Modeling Target-Side Inflection in Neural Machine Translation Aleš Tamchyna1,2 and Marion Weller-Di Marco1,3 and Alexander Fraser1 1LMU Munich, 2Memsource, 3University of Stuttgart ales.tamchyna@memsource …

Analyzing the Impact of Different Feature Queries in Active Learning for Social Robots
V Gonzalez-Pacheco, M Malfaz… – International Journal of …, 2017 – Springer
Page 1. International Journal of Social Robotics https://doi.org/10.1007/s12369-017-0449-0 Analyzing the Impact of Different Feature Queries in Active Learning for Social Robots V. Gonzalez-Pacheco1 · M. Malfaz1 · A. Castro-Gonzalez1 · JC Castillo1 · F. Alonso1 · MA Salichs1 …

PurposeNet Ontology based Question Answering (QA) System for Hindi
R Srivastava – 2017 – web2py.iiit.ac.in
… These questions are partly tackled by the dialog system which is integrated in the QA system … As said earlier we also support the QA system with a dialog system which can interact with the user before, during or after a question answering cycle …

Towards a framework for computational persuasion with applications in behaviour change
A Hunter – Argument & Computation – content.iospress.com
Persuasion is an activity that involves one party trying to induce another party to believe something or to do something. It is an important and multifaceted human facility. Obviously, sales and marketing is heavily dependent on persuasion. But many.

The synthetization of human voices
O Bendel – AI & SOCIETY, 2017 – Springer
… An AI expert recently chatted with her late friend by means of a suitable dialogue system (Nagels 2016 … autonomous systems more and more often have to make decisions of moral relevance, and these can be explicitly reasoned morally, for instance in annotated decision trees …

Affect Aware Ambient Intelligence: Current and Future Directions
C KARYOTIS, F DOCTOR, R IQBAL… – State of the Art in AI …, 2017 – books.google.com
… uncertainties and permit natural language queries [44]. Decision Trees (DT) are trees, which classify instances and were also used by a number of research teams under an AC scope [11][53]. Every node in a DT represents …

Early prediction for physical human robot collaboration in the operating room
T Zhou, JP Wachs – Autonomous Robots, 2017 – Springer
… Machine learning techniques have been applied to recognize turn-taking events automatically, mainly for spoken dialog systems. The speaker’s end-of-turn is detected by an AI agent using Support Vector Machines (Arsikere et al. 2015). Decision tree and its variants have also …

Classifying a Person’s degree of accessibility from natural body language during social human–robot interactions
D McColl, C Jiang, G Nejat – IEEE transactions on cybernetics, 2017 – ieeexplore.ieee.org
… A tenfold cross-validation was performed utilizing learning techniques from each of the following classes: 1) probabilis- tic (eg, Naïve Bayes); 2) linear (eg, logistic regression); 3) decision trees (eg, random forest); 4) lazy learning (eg, k-nearest neighbor); 5) meta-classifiers (eg …

Improvements in IITG Assamese Spoken Query System: Background Noise Suppression and Alternate Acoustic Modeling
S Shahnawazuddin, D Thotappa, A Dey… – Journal of Signal …, 2017 – Springer
… The GMM-HMM-based ASR system employed in the SQ system is developed using the Kaldi speech recognition toolkit [1, 10]. Cross-word tri-phone acoustic model training along with decision tree-based state tying is employed … Challanges for spoken dialogue systems …

Domain?independent search expertise: Gaining knowledge in query formulation through guided practice
CL Smith – Journal of the Association for Information Science …, 2017 – Wiley Online Library
… 1991a, 1991b, 1991c) studied the complexities of searching with such a system, which she described in a decision tree comprising 5 … credit hour, 100% online LIS graduate course requiring one prerequisite course on information access, which did not cover the Dialog system …

Belieavable decision making in large scale open world games for ambient characters
T Plch – 2017 – dspace.cuni.cz
Page 1. ] Charles University in Prague Faculty of Mathematics and Physics DOCTORAL THESIS [ Tomáš PLCH Believable Decision Making in Large Scale Open World Games for Ambient Characters Department of Software and Computer Science Education …

Driver Modeling for Detection and Assessment of Driver Distraction: Examples from the UTDrive Test Bed
JHL Hansen, C Busso, Y Zheng… – IEEE Signal …, 2017 – ieeexplore.ieee.org
… using on-road driving data [3], driver status monitoring systems [4], smart driver monitoring [5], conversational in-vehicle dialog systems [6], active … such as Bayesian models [33], finite-state machines and fuzzy logic [34], hidden Markov models (HMMs) [35], and decision trees [36 …

Synthesizing normalized faces from facial identity features
F Cole, D Belanger, D Krishnan, A Sarna… – IEEE Conference on …, 2017 – arxiv.org
… to a complete characterization of the maximum secret key rate achievable under a constraint on the total discussion rate. arXiv:1701.05011 [pdf, ps, other] Title: Assessing User Expertise in Spoken Dialog System Interactions …

Towards Building a Shallow Parsing Pipeline for English-Telugu Code Mixed Social Media Data
K Nelakuditi – 2017 – web2py.iiit.ac.in
Page 1. Towards Building a Shallow Parsing Pipeline for English-Telugu Code Mixed Social Media Data Thesis submitted in partial fulfillment of the requirements for the degree of MS by Research in Computational Linguistics by Kovida Nelakuditi 201125226 …

Linguistic Repetitions, Task-based Experience and A Proxy Measure of Mutual Understanding
J Reverdy, C Vogel – tara.tcd.ie
… Further exploration is needed to establish repetition’s relevance in other languages and possible application to computer-mediated interactions and dialogue systems … 41–58, 1975. [24] H. Schmid, “Probablistic part-of-speech tagging using decision trees,” in Proceedings of The …

Visually grounded interaction and language
F Strub, H de Vries, A Das, S Kottur… – Schedule …, 2017 – pdfs.semanticscholar.org
… Gallant 11: 25 AM The evolution of Visually grounded dataset Parikh 02: 00 PM Dialogue systems and RL: interconnecting language, vision and rewards Pietquin 02: 45 PM Accepted Papers 03: 15 PM Break+ Poster (2) 03: 40 PM Grounded Language Learning in a Simulated …

SmaCH: an infrastructure for smart cultural heritage environments
A Chianese, F Piccialli – … Journal of Ad Hoc and Ubiquitous …, 2017 – inderscienceonline.com
… After an experimental stage performed in our laboratories, the Decision Tree as classifier type was … With respect to a Bayesian Network classifier, the Decision Tree has an easily observable behaviour as it is possible to have an ‘explanation’ of the decision …

Recommending social platform content using deep learning
J JAXING, A HÅKANSSON, M GORETSKYY… – publications.lib.chalmers.se
… There are however a lot of different machine learning techniques which solves the problem of automatically classifying data, eg Naïve Bayes Classifier [8], Support Vector Machines (SVM) [9], [10], or Decision Tree Classifier [11] …

Foundations of Intelligent Systems: 23rd International Symposium, ISMIS 2017, Warsaw, Poland, June 26-29, 2017, Proceedings
M Kryszkiewicz, A Appice, D ?l?zak, H Rybinski… – 2017 – books.google.com
Page 1. Marzena Dominik Kryszkiewicz S´le?zak · Henryk · Annalisa Rybinski Appice Andrzej Skowron · Zbigniew W. Ras´ (Eds.) Foundations of Intelligent Systems 23rd International Symposium, ISMIS 2017 Warsaw, Poland, June 26–29, 2017 Proceedings 123 Page 2 …

AI in Informal Science Education: Bringing Turing Back to Life to Perform the Turing Test
AJ Gonzalez, JR Hollister, RF DeMara, J Leigh… – International Journal of …, 2017 – Springer
… In a “standard” CxG (as defined by Brezillon), there are five basic components in a decision tree-like contextual graph … The dialog system analyzes the several matches and determines that most of these possible matches are within the Mars context …

Phoneme Set Design for Second Language Speech Recognition
X Wang – 2017 – researchgate.net
… PDF Probability density function PDT Phonetic decision tree PLP Perceptual linear prediction ROVER Recognizer output voting error reduction RPS Reduced phoneme set … applications, such as question-answering systems and spoken dialogue systems. 1.2 The Problem …

Online/offline evolutionary algorithms for dynamic urban green space allocation problems
M Vallejo, D Corne, P Vargas – Journal of Experimental & …, 2017 – Taylor & Francis
… Instead, this type of problem has been solved traditionally using decision trees (Garcia & Sabbadin, 2006; Jeantet, Perny, & Spanjaard, 2012), influence diagrams (Guezguez, Amor, & Mellouli, 2009) and more commonly different types of Markov decision processes like partially …

A real-time ensemble classification algorithm for time series data
X Zhu, S Zhao, Y Yang, H Tang… – Agents (ICA), 2017 …, 2017 – ieeexplore.ieee.org
… REFERENCES [1] Yamada, Y.et al., Decision-Tree Induction from … 46944702. [16] T.-H. Wen, M. Gasic, N. Mrksic, P.-H. Su, D. Vandyke, and S. Young, Semantically conditioned LSTM-based natural language generation for spoken dialogue systems, arXiv:1508.01745, 2015 …

Improving Sub-phone Modeling for Better Native Language Identification With Non-native English Speech
Y Qian, K Evanini, X Wang, D Suendermann-Oeft… – Proc. Interspeech …, 2017 – oeft.de
… It also can facilitate a human-machine dialog system, which can be aware of a user’s cultural background suggested by the identified native language … The output nodes are the “senones” of HMM got by decision-tree based clustering …

Towards Interpretable Vision Systems
P Zhang – 2017 – vtechworks.lib.vt.edu
Page 1. Towards Interpretable Vision Systems Peng Zhang Dissertation submitted to the Faculty of the Virginia Polytechnic Institute and State University in partial fulfillment of the requirements for the degree of Doctor of Philosophy in Computer Engineering Devi Parikh, Chair …

Recurrent neural networks with missing information imputation for medical examination data prediction
HG Kim, GJ Jang, HJ Choi, M Kim… – Big Data and Smart …, 2017 – ieeexplore.ieee.org
… 3] J. Oh and B. Kim, “Prediction model for demands of the health meteorological information using a decision tree method,” Asian … H. Su, D. Vandyke, and S. Young, “Semantically conditioned LSTM-based natural language generation for spoken dialogue systems,” arXiv preprint …

What no robot has seen before—Probabilistic interpretation of natural-language object descriptions
D Nyga, M Picklum, M Beetz – Robotics and Automation (ICRA) …, 2017 – ieeexplore.ieee.org
… up articles about cups in online sources like Wikipedia or ask a human instructor for a definition by means of a dialog system similarly to [1]. The … They often occur in form of vectors of numerical values and are used as inputs for training classifiers like SVM or decision trees …

A Content Analysis Of The Research Approaches In Speech Emotion Recognition
T Özseven, M Dü?enci, A Durmu?o?lu – ijesrt.com
Page 1. ISSN: 2277-9655 [Ozseven* et al., 7(1): January, 2018] Impact Factor: 4.116 IC™ Value: 3.00 CODEN: IJESS7 http: // www.ijesrt.com © International Journal of Engineering Sciences & Research Technology [1] IJESRT …

Using Mandarin Training Corpus to Realize a Mandarin-Tibetan Cross-Lingual Emotional Speech Synthesis
P Wu, H Yang, Z Gan – National Conference on Man-Machine Speech …, 2017 – Springer
… Emotional speech synthesis, which has strong potential in enhancing effective communication between human and computers in spoken dialog systems [1], has … We also design a six level context-dependent label format [17] for decision tree clustering by taking into account the …

Approaches for Computational Sarcasm Detection: A Survey
L Kumar, A Somani, P Bhattacharyya – pdfs.semanticscholar.org
… (Liebrecht et al., 2013) use balanced winnow algorithm in order to deter- mine high-ranking features. (Reyes et al., 2012) use Naive Bayes and decision trees for multiple pairs of labels among irony, humor, politics and education …

Towards a Needs-Based Architecture for ‘Intelligent’Communicative Agents: Speaking with Intention
RK Moore, M Nicolao – Frontiers in Robotics and AI, 2017 – frontiersin.org
The past few years have seen considerable progress in the deployment of voice-enabled personal assistants, first on smartphones (such as Apple’s \emph{Siri}) and most recently as standalone devices in people’s homes (such as Amazon’s \emph{Alexa}). Such `intelligent’ communicative …

Web Virtual Assistant
U Chalise – 2017 – researchgate.net
… Chatterbots are typically used in dialog systems for various practical purposes including customer service or information acquisition … learning algorithms, such as decision trees, produced systems of hard if-then rules similar to existing hand-written rules …

Question Answering System: A Review On Question Analysis, Document Processing, And Answer Extraction Techniques.
FS UTOMO, N SURYANA… – Journal of Theoretical & …, 2017 – search.ebscohost.com
Page 1. Journal of Theoretical and Applied Information Technology 31st July 2017. Vol.95. No 14 © 2005 – ongoing JATIT & LLS ISSN: 1992-8645 www.jatit.org E-ISSN: 1817-3195 3158 QUESTION ANSWERING SYSTEM : A REVIEW ON …

Natural language processing in mental health applications using non-clinical texts
RA Calvo, DN Milne, MS Hussain… – Natural Language …, 2017 – cambridge.org
Page 1. Natural Language Engineering: page 1 of 37. c Cambridge University Press 2017. This is an Open Access article, distributed under the terms of the Creative Commons Attribution licence (http://creativecommons. org …

Dimensional Affect Recognition from HRV: an Approach Based on Supervised SOM and ELM
LA Bugnon, RA Calvo… – IEEE Transactions on …, 2017 – ieeexplore.ieee.org
… reviewing process [45]. In these works, the authors combined remote HR sensing and facial expressions using a voting classifier composed by SVM, k-nearest neighbor (KNN), decision trees and logistic regression. These works …

Bwibots: A platform for bridging the gap between ai and human–robot interaction research
P Khandelwal, S Zhang, J Sinapov… – … Journal of Robotics …, 2017 – journals.sagepub.com
Recent progress in both AI and robotics have enabled the development of general purpose robot platforms that are capable of executing a wide variety of complex,…

Silent speech recognition as an alternative communication device for persons with laryngectomy
GS Meltzner, JT Heaton, Y Deng… – … on Audio, Speech …, 2017 – ieeexplore.ieee.org
… A data driven decision tree (using the KALDI toolkit decision tree algorithm) is then used to cluster the triphone models for the observed training data and create triphone models for new phoneme com- binations not seen during training …

More than I ever wanted or just good enough? User expectations and subjective quality perception in the context of networked multimedia services
A Sackl, R Schatz, A Raake – Quality and User Experience, 2017 – Springer
… In Hartikainen et al. (2004), the authors present a study about the evaluation of a spoken dialogue system via SERVQUAL questionnaires. Five service quality dimensions were evaluated by the test participants: tangibles, reliability, responsiveness, assurance and empathy …

Computational modeling of turn-taking dynamics in spoken conversations
SA Chowdhury – 2017 – eprints-phd.biblio.unitn.it
… 97 6.7 Decision Tree presenting the features and their values for between speaker si- lence. -p represents preceding segment; -s representssucceedingsegment . . 100 6.8 Decision Tree presenting the features and their values for within speaker si- lence …

Monday, May 15, 2017
SL Datasets, BD Analytics – ieeexplore.ieee.org
Page 1. TECHNICAL PAPERS Scroll to the title and select a Blue link to open a paper. After viewing the paper, use the bookmarks to the left to return to the beginning of the Table of Contents. Monday, May 15, 2017 Session …

Online Help Seeking in Computer Science Education
Q Hao – 2017 – works.bepress.com
… Page 18. 5 ? Target Data: 983 questions asked by the participants on an online question and answer platform ? Data Analysis: Naive Bayes Multinomial, Logistic Regression, Support Vector Machines, and Boosted Decision Tree Page 19. 6 CHAPTER 2 LITERATURE REVIEW …

Využití uživatelské odezvy pro zvýšení kvality ?e?ové syntézy
V Hude?ek – 2017 – dspace.cuni.cz
… cess may look like. The dialogue system pronounces user’s name incorrectly. The user then corrects it and the system learns from that. The transcriptions of the … Traditionally, the g2p task was solved using decision trees models. It can also be formulated as a problem of translat …

Neural network methods for natural language processing
Y Goldberg – Synthesis Lectures on Human Language …, 2017 – morganclaypool.com
… Semantic Role Labeling Martha Palmer, Daniel Gildea, and Nianwen Xue 2010 Spoken Dialogue Systems Kristiina Jokinen and Michael McTear 2009 Introduction to Chinese Natural Language Processing Kam-Fai Wong, Wenjie Li, Ruifeng Xu, and Zheng-sheng Zhang 2009 …

The Official Rulebook for Choice in Video Games: An Examination of Choice in Modern Narrative Games
T Paulley – scholarworks.bellarmine.edu
… agency” where they were allowed to interact with Shepard “at the level of attitude rather than identity” (5). This is seen in the game’s dialogue system where the attitude and personality of Shepard is mutable by the player but …

Selected Distinguishing Properties of WisTech IGrC Models
A Jankowski – Interactive Granular Computations in Networks and …, 2017 – Springer
This assumption, among others, is understood in such a way that all interactions that are analyzed by us are reduced to physical phenomena.

Sarcasm Detection Using Sentiment Flow Shifts
E Filatova – 2017 – pdfs.semanticscholar.org
… k-NN 0.469 0.445 0.552 SVM (linear) 0.670 1.000 0.581 SVM (RBF) 0.522 0.512 0.581 Decision Tree 0.606 0.691 0.534 Random Forest 0.618 0.660 0.596 AdaBoost 0.607 0.651 0.571 Logistic Regr … “yeah right”: Sarcasm recognition for spoken dialogue systems …

Low-resource Multi-task Audio Sensing for Mobile and Embedded Devices via Shared Deep Neural Network Representations
P Georgiev, S Bhattacharya, ND Lane… – Proceedings of the ACM …, 2017 – dl.acm.org
… audio stream, including: (i) recognize if spoken words are present (and not any other type of sound); (ii) perform spoken keyword spotting (as all commands should begin with the same key word); and, (iii) speech recognition, along with additional dialog system analysis that …

Error Analysis in an Automated Narrative Information Extraction Pipeline
J Valls-Vargas, J Zhu, S Ontanon – IEEE Transactions on …, 2017 – ieeexplore.ieee.org
… Fig. 1. Parse tree annotated by Voz after the mention extraction process. Margaretha & DeVault [37] tackle the issue of automated eval- uation of pipeline architectures in natural language dialogue systems using a Wizard-of-Oz approach and simulations of the pipeline process …

Improving scalability of inductive logic programming via pruning and best-effort optimisation
M Kazmi, P Schüller, Y Sayg?n – Expert Systems with Applications, 2017 – Elsevier
… real numbers. Some popular classifiers used for processing natural language include Naive Bayes, Decision Trees, Neural Networks, and Support Vector Machines (SVMs) (Dumais, Platt, Heckerman, & Sahami, 1998). In this …

Design and development of a cognitive assistant for the architecting of earth observing satellites
A Virós Martin – 2017 – upcommons.upc.edu
… 18 3.2 Historical database schema . . . . . 24 3.3 Decision tree for the data mining algorithm . . . . . 29 3.4 Smallportionoftheontology . . . . . 30 3.5 Screen-shotoftheiFEEDInterface . . . . . 43 …

Voice activity detection and garbage modelling for a mobile automatic speech recognition application
M Ishaq – 2017 – aaltodoc.aalto.fi
… recognition. In 2000s, the integration of full semantics model and text-to-speech synthesis system with the very large vocabulary system happened, which enabled the spoken dialog systems with multiple input-output approaches …

Autonomous Agents Modelling Other Agents: A Comprehensive Survey and Open Problems
SV Albrecht, P Stone – arXiv preprint arXiv:1709.08071, 2017 – arxiv.org
… goals and plans of agents (Schmidt et al., 1978) were applied in automated dialogue systems to understand and disambiguate the … This allows us to use deterministic structures such as decision trees and deterministic state automata, for which efficient learning algorithms exist …

COGNIMUSE: a multimodal video database annotated with saliency, events, semantics and emotion with application to summarization
A Zlatintsi, P Koutras, G Evangelopoulos… – EURASIP Journal on …, 2017 – Springer
… Next, a shallow syntactic parser that performed POS tagging was used, specifically, a decision-tree-based probabilistic tagger [70]. For more information, we refer the reader to TMM13 [12]. 3.3 Audio events and visual actions annotation …

Combining augmented statistical noise suppression and framewise speech/non-speech classification for robust voice activity detection
Y Obuchi – APSIPA Transactions on Signal and Information …, 2017 – cambridge.org
… more precisely. It is called supervised training. In this paper, we investi- gate three model-based supervised classifiers: decision tree (DT), SVM, and CNN. For all clusterers and classifiers, the same feature set is used. The feature …

Helping users learn about social processes while learning from users: developing a positive feedback in social computing
VSS Pillutla – 2017 – search.proquest.com
Helping Users Learn About Social Processes While Learning from Users: Developing a Positive Feedback in Social Computing. Abstract. Social computing is concerned with the interaction of social behavior and computational systems …

Natural language generation in the context of multimodal interaction in Portuguese: Data-to-text based in automatic translation
JC Pereira – 2017 – ria.ua.pt
Page 1. Universidade de Aveiro Departamento de Electrónica, Telecomunicaç˜oes e Informática 2017 das Universidades de Aveiro, Minho e Porto Programa de Doutoramento em Informática José Casimiro Pereira Geraç˜ao de Linguagem Natural noÂmbito de …

Overcoming the limitations of statistical parametric speech synthesis
T Merritt – 2017 – era.lib.ed.ac.uk
… monly referred to as text-to-speech (TTS). Speech synthesis has many useful applica- tions such as; providing a means of interaction with dialog systems, automatic pro … This is a practice typically performed during decision tree regression in HMM synthesis …

Do you speak to a human or a virtual agent? automatic analysis of user’s social cues during mediated communication
M Ochs, N Libermann, A Boidin… – Proceedings of the 19th …, 2017 – dl.acm.org
… It’s why we have chosen to use the Random Forest approach. Such a method has already been used in a similar task to identify relevant social cues in body movements [11]. We have used the random forest algorithm with 100 decision tree …

Deriving and Exploiting Situational Information in Speech: Investigations in a Simulated Search and Rescue Scenario
S Mokaram Ghotoorlar – 2017 – etheses.whiterose.ac.uk
Page 1. Deriving and Exploiting Situational Information in Speech: Investigations in a Simulated Search and Rescue Scenario Saeid Mokaram Department of Computer Science The University of Sheffield PhD Thesis submitted for the degree of Doctor of Philosophy …

A Theory of Model Selection in Reinforcement Learning
N Jiang – 2017 – deepblue.lib.umich.edu
… tant applications of Artificial Intelligence (AI), including news recommendation and online advertising, dialog systems, self-driving cars, robots for daily life, adaptive … nite (eg, for decision trees), cross-validation-type methods may exceed the statisti …

Deep Memory Networks for Natural Conversations
??? – 2017 – s-space.snu.ac.kr
… of possible implementations. The components I, G, O and R can potentially use any existing ideas from the machine learning literature, eg, make use of your favorite models (SVMs, decision trees, etc.). I component: Component I can make use of standard pre-processing, eg …

A Framework For Enhancing Speaker Age And Gender Classification By Using A New Feature Set And Deep Neural Network Architectures
A Abumallouh – 2017 – scholarworks.bridgeport.edu
… DNNs Deep Neural Networks DT Decision Tree GRNNs General Regression Neural Networks HMMs Hidden Markov Models … SCM SDC Class Models SDS Spoken Dialogue Systems SSM SDC Speaker Models T-MFCCs Transformed Mel-Frequency Cepstral Coefficients …

Developing Semantic Role Labeler for Hindi and Urdu
MA Nomani – 2017 – web2py.iiit.ac.in
… years appears to be motivated both by the gains in efficiency in analyzing the structure of the sentence to remove ambiguity and by its potential usefulness in several NLP applications like machine translation, semantic role labeling, discourse analysis and dialogue systems. 2 …

Crowdtesting for chatbots: a market analysis. Empirical activity with App-Quality srl
A TRANI – 2017 – politesi.polimi.it
Page 1. POLITECNICO DI MILANO School of Industrial and Information Engineering Master of science in Management Engineering – Digital Business and Market Innovation AY 2016/17 CROWD TESTING FOR CHATBOTS: A MARKET ANALYSIS …

Characterisation of voice quality of Parkinson’s disease using differential phonological posterior features
M Cernak, JR Orozco-Arroyave, F Rudzicz… – Computer Speech & …, 2017 – Elsevier
… data. The remaining 10% subset was used for cross-validation. The triphone models are tied with decision tree state clustering based on the minimum description length (MDL) criterion (Shinoda and Watanabe, 1997). The MDL …

Painting Pictures with Words-From Theory to System
R Coyne – 2017 – search.proquest.com
… Ulysse [Godreaux et al., 1999] is an interactive spoken dialog system used to navigate in virtual worlds … It sequences events with learned decision trees from TimeML [Pustejovsky et al., 2003] and lls an ACCIDENT frame with slots for objects, road, collisions …

Theory and Applications of Models of Computation
TV Gopal, G Jäger, S Steila – 2017 – Springer
Page 1. TV Gopal Gerhard Jäger Silvia Steila (Eds.) 123 LNCS 10185 14th Annual Conference, TAMC 2017 Bern, Switzerland, April 20–22, 2017 Proceedings Theory and Applications of Models of Computation Page 2. Lecture Notes in Computer Science 10185 …

Automatic assessment of depression based on visual cues: A systematic review
A Pampouchidou, P Simos, K Marias… – IEEE Transactions …, 2017 – ieeexplore.ieee.org
Page 1. 1949-3045 (c) 2017 IEEE. Translations and content mining are permitted for academic research only. Personal use is also permitted, but republication/ redistribution requires IEEE permission. See http://www.ieee.org …

Automatic Text Simplification
H Saggion – Synthesis Lectures on Human Language …, 2017 – morganclaypool.com
… 2010 Spoken Dialogue Systems Kristiina Jokinen and Michael McTear 2009 … simplification. ?eir approach consists of training a decision-tree learning algorithm (C4.5 [Quinlan, 1993]) to classify a sentence into split or non- split …

A joint deep model of entities and documents for cumulative citation recommendation
L Ma, D Song, L Liao, Y Ni – Cluster Computing, 2017 – Springer
Page 1. Cluster Comput DOI 10.1007/s10586-017-1273-x A joint deep model of entities and documents for cumulative citation recommendation Lerong Ma1,2 · Dandan Song1 · Lejian Liao1 · Yao Ni1 Received: 29 June 2017 …

Thesis Material-Rasmus Dall
R Dall – 2017 – datashare.is.ed.ac.uk
… 29 2.5 A small sample decision tree … CSS Conversational Speech Synthesis DM Discourse Marker DNN Deep Neural Network DT Decision Tree DP Decision Parameter EM Expectation-Maximisation F0 Fundamental Frequency f-RNN Full Output Layer RNN …

Advanced data exploitation in speech analysis: An overview
Z Zhang, N Cummins, B Schuller – IEEE Signal Processing …, 2017 – ieeexplore.ieee.org
… For speech processing, crowdsourcing has been widely employed for a range of tasks, including speech data col- lection/acquisition, speech annotation, speech perception, assessment of speech synthesis, and dialog system evalua- tion [15], [26] …

Assessing Adaptive Learning Styles in Computer Science Through a Virtual World
N Kury – 2017 – search.proquest.com
… 62. 3.3: Example of Dialogue XML ….. 64. 3.4: Class Diagram of Dialogue System ….. 65. 3.5: In-Game View of Dialogue Window ….. 66 …

Neural Models for Information Retrieval
B Mitra, N Craswell – arXiv preprint arXiv:1705.01509, 2017 – arxiv.org
Page 1. Neural Models for Information Retrieval Bhaskar Mitra Microsoft, UCL? Cambridge, UK bmitra@microsoft.com Nick Craswell Microsoft Bellevue, USA nickcr@microsoft.com Abstract Neural ranking models for information …

Natural Language Processing for Social Media
A Farzindar, D Inkpen – Synthesis Lectures on Human …, 2017 – morganclaypool.com
… Semantic Role Labeling Martha Palmer, Daniel Gildea, and Nianwen Xue 2010 Spoken Dialogue Systems Kristiina Jokinen and Michael McTear 2009 Introduction to Chinese Natural Language Processing Kam-Fai Wong, Wenjie Li, Ruifeng Xu, and Zheng-sheng Zhang 2009 …

Movement Data
S Hoogervorst – pure.tue.nl
Page 1. Eindhoven University of Technology MASTER Predicting website visitor gender and age with mouse movement data Hoogervorst, SJ Award date: 2016 Disclaimer This document contains a student thesis (bachelor’s …

Heterogeneous resource mobile sensing: computational offloading, scheduling and algorithm optimisation
P Georgiev – 2017 – cl.cam.ac.uk
… audio stream, including: (i) recognise if spoken words are present (and not any other type of sound); (ii) perform spoken keyword spotting (as all commands are begun with the same starting word); and, (iii) speech recognition, along with additional dialogue system analysis that …

Better Education Through Improved Reinforcement Learning
TS Mandel – 2017 – digital.lib.washington.edu
Page 1. cGCopyright 2017 Travis Scott Mandel Page 2. Better Education Through Improved Reinforcement Learning Travis Scott Mandel A dissertation submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy University of Washington 2017 …

Propositional Knowledge: Acquisition and Application to Syntactic and Semantic Parsing
B Cabaleiro Barciela – 2017 – e-spacio.uned.es
Page 1. Thesis for the Degree of Doctor of Philosophy 2017 Propositional Knowledge: Acquisition and Application to Syntactic and Semantic Parsing Bernardo Cabaleiro Barciela University Master’s Degree in Languages and Computer Systems (National Distance Education …

Maximum-a-Posteriori-Based Decoding for End-to-End Acoustic Models
N Kanda, X Lu, H Kawai – IEEE/ACM Transactions on Audio …, 2017 – ieeexplore.ieee.org
… DNN-HMM modeling normally requires redun- dant GMM-HMM training simply to obtain the training labels for DNNs. It also requires complicated decision tree building and pronunciation modeling to achieve state-of-the-art results …

Learning Logic Rules From Text Using Statistical Methods For Natural Language Processing
M KAZMI – 2017 – peterschueller.com
… belongs to a class: f( ? x) = confidence(class) Some popular classifiers used in NLP include Naive Bayes, Decision Trees, Neural Networks … Some popular classifiers used for processing natural language include Naive Bayes, Decision Trees, Neural Networks (NNs) …

Computational models for semantic textual similarity
A González Aguirre – 2017 – addi.ehu.es
Page 1. UNIVERSITY OF THE BASQUE COUNTRY Computer Languages and Systems PhD Thesis Computational Models for Semantic Textual Similarity Aitor Gonzalez-Agirre 2017 (c)2017 AITOR GONZALEZ AGIRRE Page 2. Page 3 …

HCI International 2017–Posters’ Extended Abstracts: 19th International Conference, HCI International 2017, Vancouver, BC, Canada, July 9–14, 2017 …
C Stephanidis – 2017 – books.google.com
… Using Tags . . . . . 450 Junko Itou, Rina Tanaka, and Jun Munemori Collection of Example Sentences for Non-task-Oriented Dialog Using a Spoken Dialog System and Comparison with Hand-Crafted DB . . . . 458 Yukiko Kageyama …

Deep Learning for Distant Speech Recognition
M Ravanelli – arXiv preprint arXiv:1712.06086, 2017 – arxiv.org
… video classification), machine translation, as well as in natural language processing (for dialogue systems, question answering, image captioning … for instance, the development of real-time speech recognizers or low- latency dialogue systems …

Leveraging Legal Stringency on Artificial Intelligence Applications-A’Copyright Law on Artificial Intelligence’Debate
P Bhattacharya – 2017 – papers.ssrn.com
… Image and voice recognition are one of the examples of deep learning. 42 An example of an automated online assistant having a text based dialog system, available in CC0 1.0 Universal (CC0 1.0) Public Domain Dedication …

Cheminformatics Tools for Enabling Metabolomics
YD Feunang – 2017 – era.library.ualberta.ca
Page 1. Cheminformatics Tools for Enabling Metabolomics by Yannick Djoumbou Feunang A thesis submitted in partial fulfillment of requirements for the degree of Doctor of Philosophy in Microbiology and Biotechnology Department of Biological Sciences University of Alberta …

Generating variations in a virtual storyteller
SM Lukin – 2017 – search.proquest.com
… 20. 2.1.3 Overgenerate and Rank . . . . . 25. 2.2 Narrative and Dialogue Systems . . . . . 27. 2.2.1 Narrative Prose Generation … Previous research on NLG of linguistic style shows that dialogue systems are more. 22 …

Discovery of topic flows of authors
YS Jeong, SH Lee, G Gweon, HJ Choi – The Journal of Supercomputing, 2017 – Springer
Page 1. J Supercomput DOI 10.1007/s11227-017-2065-z Discovery of topic flows of authors Young-Seob Jeong1 · Sang-Hun Lee2 · Gahgene Gweon3 · Ho-Jin Choi4 © The Author(s) 2017. This article is an open access publication …

Psychophysiological measures of mental effort and emotion within user research
CR Meusel – 2017 – search.proquest.com
Psychophysiological Measures of Mental Effort and Emotion within User Research. Abstract. Psychophysiological measures have potential to aid the discipline of user research, but are currently under-utilized. Currently, across …

Automated Feature Engineering for Deep Neural Networks with Genetic Programming
J Heaton – 2017 – search.proquest.com
Automated Feature Engineering for Deep Neural Networks with Genetic Programming. Abstract. Feature engineering is a process that augments the feature vector of a machine learning model with calculated values that are designed …

Learning from Temporally-Structured Human Activities Data
ZC Lipton – 2017 – search.proquest.com
… 131. 8.1 Introduction . . . . . 131. 8.2 Task-completion dialogue systems . . . . . 133. viii. 8.2.1 Dialog-acts … (black). . . . 128. Figure 8.1: Components of a dialogue system . . . . . 134 …

Personalizing recurrent-neural-network-based language model by social network
HY Lee, BH Tseng, TH Wen, Y Tsao, HY Lee… – IEEE/ACM Transactions …, 2017 – dl.acm.org
Page 1. IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, VOL. 25, NO. 3, MARCH 2017 519 Personalizing Recurrent-Neural- Network-Based Language Model by Social Network Hung-Yi …

A New Classification Framework to Evaluate the Entity Profiling on the Web: Past, Present and Future
AA Barforoush, H Shirazi, H Emami – ACM Computing Surveys (CSUR), 2017 – dl.acm.org
Page 1. 39 A New Classification Framework to Evaluate the Entity Profiling on the Web: Past, Present and Future AHMAD ABDOLLAHZADEH BARFOROUSH, HOSSEIN SHIRAZI, and HOJJAT EMAMI, Malek Ashtar University of Technology …

Theory and Algorithms for Learning with Stratified Decisions
G DeSalvo – 2017 – search.proquest.com
… needed to achieve a higher performance. However, even with a relatively large. number of training samples, these more complex decision trees are prone to overfitting … spoken-dialog systems, search engine design, astronomical event detection, active …

Can We Speculate Running Application With Server Power Consumption Trace?
Y Li, H Hu, Y Wen, J Zhang – IEEE transactions on cybernetics, 2017 – ieeexplore.ieee.org
… The canonical classifiers tested here are listed as follows: nearest neighbors, linear SVM, RBF SVM, decision tree, random forest, AdaBoost, naive Bayes, LDA, and QDA [36]. Parameter settings for these classifiers are tuned manually …

Building ICT-based Information Flows to Improve Citizen-Government Engagement
D Chakraborty – 2017 – cse.iitd.ac.in
… Medhi et al. compare an IVR spoken dialogue system with a rich multimedia device for mobile banking tasks [31]. They find that while users have no hesitancy speaking to the IVR system, challenges with accent, vocabulary …

(Visited 131 times, 1 visits today)