SVM (Support Vector Machine) & Dialog Systems 2016


Notes:

In machine learning, support vector machines (SVMs) are supervised learning models with associated learning algorithms that analyze data and recognize patterns, used for classification and regression analysis.

  • dialog agent
  • natural language dialog system
  • natural language understanding module

Resources:

  • tweetyproject.org .. java libraries for logical aspects of artificial intelligence and knowledge representation

Wikipedia:

See also:

100 Best Support Vector Machine Videos


Emotion and its triggers in human spoken dialogue: Recognition and analysis
N Lubis, S Sakti, G Neubig, T Toda… – Situated Dialog in …, 2016 – Springer
… Therefore, to build a natural spoken dialogue system, it is essential to consider emotional aspects, which should be done not only … In this paper, we propose a method of automatic recognition of emotion using support vector machine (SVM) and present further analysis regarding …

Dialogue management for user-centered adaptive dialogue
S Ultes, H Dikme, W Minker – Situated Dialog in Speech-Based Human …, 2016 – Springer
… 1 Introduction. Most Spoken Dialogue Systems (SDS) are not capable of automatically adapting to changing situations, eg, a changing environment or changing user needs. … Schmitt et al. [10] applied a Support Vector Machine [16] (SVM) for estimating the Interaction Quality …

An intelligent assistant for high-level task understanding
M Sun, YN Chen, AI Rudnicky – … of the 21st International Conference on …, 2016 – dl.acm.org
… Conventional multi-domain dialog systems passively select one domain from multiple domains according to a user in- put, ignoring relationships between domains and the ultimate user intention behind … For MULTLAB, we used support vector machine (SVM) with linear kernel. …

Automatic Recognition of Conversational Strategies in the Service of a Socially-Aware Dialog System.
R Zhao, T Sinha, AW Black, J Cassell – SIGDIAL Conference, 2016 – aclweb.org
… By the same token, we believe this work to be crucial if we wish to develop a socially-aware dialog system that can … The following ta- ble shows our comparison with other standard ma- chine learning algorithms such as Support Vector Machine (SVM) and Naive Bayes (NB …

Evaluation of statistical POMDP-based dialogue systems in noisy environments
S Young, C Breslin, M Gaši?, M Henderson… – Situated Dialog in …, 2016 – Springer
… Both the conventional baseline and the statistical dialogue system share a common architecture and a common set of understanding and … extracts n-grams from the confusion networks output by the recogniser and uses a bank of support vector machine (SVM) classifiers to …

Adobe-MIT submission to the DSTC 4 Spoken Language Understanding pilot task
F Dernoncourt, JY Lee, TH Bui, HH Bui – arXiv preprint arXiv:1605.02129, 2016 – arxiv.org
… System 3 is based on a support vector machine (SVM) classifier to recognize the speech acts: the fea- tures are the 5000 most common unigrams, bigrams, trigrams, as well as a … In Proceedings of the 7th International Workshop on Spoken Dialogue Systems (IWSDS), 2016. …

Analysis of emotional speech—A review
P Gangamohan, SR Kadiri… – Toward Robotic Socially …, 2016 – Springer
… In: Affective dialogue systems. … In: INTERSPEECH. Pittsburgh, Pennsylvania, pp 17–21. 108. Schuller B, Rigoll G, Lang M (2004) Speech emotion recognition combining acoustic features and linguistic information in a hybrid support vector machine-belief network architecture. …

Question answering system, approaches and techniques: A review
AM Pundge, SA Khillare… – International Journal of …, 2016 – academia.edu
… GUS Bobrow et al.[14] Closed Domain A frame-driven dialog system Genial Under stander system also used structured database … Mostly all Statistical Based QA system applied a statistical technique in QA system such as Support vector machine classifier, Bayesian Classifiers …

Question detection from acoustic features using recurrent neural network with gated recurrent unit
Y Tang, Y Huang, Z Wu, H Meng… – Acoustics, Speech and …, 2016 – ieeexplore.ieee.org
… Second, in most spoken dialog systems, automatic speech recognition (ASR) is the foremost step whose performance will have huge … coefficients (MFCCs) for detecting interrogative intonation in Mandarin and achieved improved performance using support vector machine (SVM …

Toward incremental dialogue act segmentation in fast-paced interactive dialogue systems
R Manuvinakurike, M Paetzel, C Qu… – Proceedings of the …, 2016 – pub.uni-bielefeld.de
… It’s important to allow users to speak naturally to spoken dialogue systems. … resulting DA segment is classified into one of 18 DA labels using an SVM (Support Vector Machine) classifier implemented in Weka (Hall et al., 2009). 4.1 Features …

Multi-objective heuristic feature selection for speech-based multilingual emotion recognition
C Brester, E Semenkin, M Sidorov – Journal of Artificial Intelligence …, 2016 – degruyter.com
… algorithm. 3 Speech-based Emotion Recogni- tion Problem One of the obvious ways to improve the intel- lectual abilities of spoken dialogue systems is that related to their personalization. While … 19]: – Support Vector Machine (SMO). To …

Topic detection and tracking for conversational content by using conceptual dynamic latent Dirichlet allocation
JF Yeh, YS Tan, CH Lee – Neurocomputing, 2016 – Elsevier
… Experimental results revealed that the proposed approach outperformed the traditional DLDA and LDA and support vector machine models, in addition to achieving … A multidomain conversational dialogue system focuses on processing goal-oriented dialogue and chat [13]. …

Identification of nonliteral language in social media: A case study on sarcasm
S Muresan, R Gonzalez?Ibanez… – Journal of the …, 2016 – Wiley Online Library
… and negative?”. We used three standard classifiers often employed in sentiment classification: naïve Bayes (NB), support vector machine with sequential minimal optimization (SVM), and logistic regression (LogR). For features …

Sentiment Analysis of Twitter data using Hybrid Method of Support Vector Machine and Ant Colony Optimization
J Kaur, SS Sehra, SK Sehra – International Journal of …, 2016 – search.proquest.com
… This classification is performed by using a hybrid strategy of Machine Learning algorithm Support Vector Machine (SVM) and Ant Colony … Sentiment analysis finds application in systems that present summarization of reviews, dialogue systems, analysis of media applications. …

A Two-Stage Combining Classifier Model for the Development of Adaptive Dialog Systems
D Griol, JA Iglesias, A Ledezma… – International journal of …, 2016 – World Scientific
… Several works have also recently proposed the use of this kind of algorithms for enhancing dialog systems with emotion recognition and eye … works: a multi- nomial naive Bayes classifier, an n-gram-based clas- sifier, a decision tree classifier, a support vector machine classifier, a …

MobileSSI: Asynchronous fusion for social signal interpretation in the wild
S Flutura, J Wagner, F Lingenfelser… – Proceedings of the 18th …, 2016 – dl.acm.org
… the raw streams (see Section 3.2) when voice activity is de- tected in the audio channel. Support Vector Machine (SVM) classifiers recognize laughter events in the two channels that are combined using an asynchronous fusion scheme (see Sec- tion 3.3). …

Assessing user expertise in spoken dialog system interactions
E Ribeiro, F Batista, I Trancoso, J Lopes… – Advances in Speech …, 2016 – Springer
… Let’s Go Bus Information System [15], which provides information about bus schedules, through spoken telephonic interaction with a dialog system. … From the multiple classification approaches that could be used, we opted Support Vector Machine (SVMs) [3], since it is a widely …

Predicting User Satisfaction from Turn-Taking in Spoken Conversations.
SA Chowdhury, EA Stepanov, G Riccardi – INTERSPEECH, 2016 – sensei-conversation.eu
… tutor- ing [4]. In SDS, user satisfaction is used as one of the metrics to assess the quality of a dialog system [5, 6 … Classification and Evaluation A Sequential Minimal Optimization (SMO), a support vector machine implementation of weka [37], is used to train the clas- sifiers with …

Prediction of Prospective User Engagement with Intelligent Assistants.
S Sano, N Kaji, M Sassano – ACL (1), 2016 – aclweb.org
… Such user behaviors are rarely observed in conventional ex- perimental environments, where dialogue systems … The dropout prediction is performed using lin- ear support vector machine (SVM) (Fan et al., 2008), while the engagement level prediction is performed using support …

Intensified Sentiment Analysis of Customer Product Reviews Using Acoustic and Textual Features
S Govindaraj, K Gopalakrishnan – ETRI Journal, 2016 – etrij.etri.re.kr
… His research areas of interest include human–computer interaction and spoken dialogue systems. … The popular support vector machine (SVM) classifier is used for the automatic prediction of intensified customer sentiments about products. …

Fostering user engagement in face-to-face human-agent interactions: a survey
C Clavel, A Cafaro, S Campano… – Toward Robotic Socially …, 2016 – Springer
… In: Lee GG, Mariani J, Minker W, Nakamura S (eds) Spoken dialogue systems for ambient environments. … Schuller B, Rigoll G, Lang M (2004) Speech emotion recognition combining acoustic features and linguistic information in a hybrid support vector machine-belief network …

Zara: A Virtual Interactive Dialogue System Incorporating Emotion, Sentiment and Personality Recognition.
P Fung, A Dey, FB Siddique, R Lin… – COLING …, 2016 – pdfs.semanticscholar.org
… As the availability of interactive dialogue systems is on a rise, people are getting more accustomed to talking to machines … For baseline, we use Support Vector Machine (SVM) classifier with a linear kernel using the INTER- SPEECH 2009 emotion feature set (Schuller et al., 2009 …

Cross-corpus speech emotion recognition based on transfer non-negative matrix factorization
P Song, W Zheng, S Ou, X Zhang, Y Jin, J Liu… – Speech …, 2016 – Elsevier
… With the development of computer technologies, the demands for emotion recognition in new spoken dialogue systems are very … pattern recognition and machine learning, have been developed to implement the classification function, eg, support vector machine (SVM), neural …

Transfer of corpus-specific dialogue act annotation to iso standard: Is it worth it?
SA Chowdhury, EA Stepanov, G Riccardi – LREC, 2016 – lrec-conf.org
… of applications of DA analysis is quite wide and includes conversation summa- rization (both spoken and written), dialogue systems, etc.; and … For the dialogue act classification, we use Sequential Min- imal Optimisation (SMO), a support vector machine im- plementation, with its …

Layered hidden Markov models to recognize activity with built-in sensors on Android smartphone
YS Lee, SB Cho – Pattern Analysis and Applications, 2016 – Springer
… Min and Cho [11] proposed a method to recognize activities by combining multiple classifiers such as support vector machine (SVM) and Bayesian network (BN). Park … al. used hierarchical HMM for spoken dialogue system [27]. …

Creating annotated dialogue resources: Cross-domain dialogue act classification
D Amanova, V Petukhova, D Klakow – Inform, 2016 – lsv.uni-saarland.de
… The recognition of the intentions encoded in user utterances is one of the most important aspects of language under- standing for a dialogue system. … Support Vector Machine (SVM) (Boser et al., 1992) clas- sifier training was performed using the scikit-learn imple- mentation8. …

Exploring Convolutional and Recurrent Neural Networks in Sequential Labelling for Dialogue Topic Tracking.
S Kim, RE Banchs, H Li – ACL (1), 2016 – aclweb.org
… Although they don’t aim at building components in dialogue systems di- rectly, the human behaviours learned from the con- versations can suggest directions for further ad … The first baseline uses support vector machine (SVM) (Cortes and Vapnik, 1995) models trained …

Topic Categorization Based on Collectives of TermWeighting Methods for Natural Language Call Routing
RB Sergienko, M Shan, W Minker, ES Semenkin… – 2016 – elib.sfu-kras.ru
… spoken dialogue system design [2]. In this work we treat call routing as an example of a text classification application In … After text preprocessing, machine learning algorithms are applied for the classification, such as k-NN, support vector machine (SVM) [11], Rocchio classifier …

A comprehensive study of classification techniques for sarcasm detection on textual data
AD Dave, NP Desai – Electrical, Electronics, and Optimization …, 2016 – ieeexplore.ieee.org
… problems for many Natural Language Processing based system such as online review summarization systems, dialogue systems or brand … 16], [17], [18], [19],[20] and [21] have used traditional supervised classification techniques like Support Vector Machine (SVM), Conditional …

Comparing dialogue strategies for learning grounded language from human tutors
Y Yu, O Lemon, A Eshghi – SEMDIAL 2016 JerSem, 2016 – pdfs.semanticscholar.org
… hw. ac. uk Arash Eshghi Interaction Lab Heriot-Watt University a. eshghi@ hw. ac. uk Abstract We address the problem of interac- tively learning perceptually grounded word meanings in a multimodal dialogue system. Human …

Recurrent convolutional neural networks for structured speech act tagging
T Ushio, H Shi, M Endo, K Yamagami… – … Workshop (SLT), 2016 …, 2016 – ieeexplore.ieee.org
… Their experiment showed classifica- tion accuracy to be enhanced by 14% over the conventional method based on a Support Vector Machine. However, their method, since it lacks contextual information, cannot capture 978-1-5090-4903-5/16/$31.00 ©2016 IEEE 518 …

Recent Advances on Human-Computer Dialogue
X Wang, C Yuan – CAAI Transactions on Intelligence Technology, 2016 – Elsevier
… For a more comprehensive survey on traditionally dialogue systems, especially on POMDP based pipeline dialogue systems, please read … Lots of supervised classifiers, including Support Vector Machine (SVM) [9], Maximum Entropy (ME) [10], Deep Neural Network (DNN) [11 …

Hybrid recognition technology for isolated voice commands
G Bartiši?t?, K Ratkevi?ius, G Paškauskait? – … Systems Architecture and …, 2016 – Springer
… K-Nearest Neighbour kNN), decision tree (Decision Tree), multilayered neural network (Multilayer Perceptron MP), support vector classifier (support vector machine SVM), OneR and … 1. Suendermann, D., Pieraccini, R.: SLU in commercial and research spoken dialogue systems. …

Exploiting turn-taking temporal evolution for personality trait perception in dyadic conversations
MH Su, CH Wu, YT Zheng – IEEE/ACM Transactions on Audio …, 2016 – ieeexplore.ieee.org
… Compared with conventional HMM and support vector machine-based methods, the proposed approach achieved a more favorable performance according to a statistical significance test. The encouraging results confirm the usability of this system for future applications. …

Asynchronous and Event-based Fusion Systems for Affect Recognition on Naturalistic Data in Comparison to Conventional Approaches
F Lingenfelser, J Wagner, J Deng… – IEEE Transactions …, 2016 – ieeexplore.ieee.org
Page 1. 1949-3045 (c) 2016 IEEE. Personal use is permitted, but republication/ redistribution requires IEEE permission. See http://www.ieee.org/ publications_standards/publications/rights/index.html for more information. This …

Spoken language understanding for service robotics in italian
A Vanzo, D Croce, G Castellucci, R Basili… – AI* IA 2016 Advances in …, 2016 – Springer
… Spoken Language Understanding (SLU) for interactive dialogue systems acquires a specific nature when applied to Interactive Robotics. … This module is realized through a learn-to-rank approach, where a Support Vector Machine exploiting a combination of linguistic kernels is …

CogWatch: Automatic prompting system for stroke survivors during activities of daily living
EMD Jean-Baptiste, P Rotshtein, M Russell – Journal of Innovation in Digital …, 2016 – Elsevier
This paper presents CogWatch – an automatic prompting system designed to guide stroke survivors during activities of daily living, such as tea-making. In order.

User-centred spoken dialogue management
F Nothdurft, S Ultes, W Minker – Next Generation Intelligent Environments, 2016 – Springer
… a general quality metric, features have to be domain-independent, ie not dependent on the task domain of the dialogue system. … Applying a Support Vector Machine [51] (SVM) for estimating the Interaction Quality achieved an unweighted average recall of 0.59 when including …

The comprehension of figurative language: what is the influence of irony and sarcasm on NLP techniques?
L Weitzel, RC Prati, RF Aguiar – Sentiment Analysis and Ontology …, 2016 – Springer
… sighted users; automatic report generation (possibly multilingual); machine translation; plagiarism detection tools; email understanding and dialogue systems [5 … Their evaluation was performed using the Maximum Entropy (MaxEnt) and Support Vector Machine (SVM) classifiers. …

Text analytics in industry: Challenges, desiderata and trends
A Ittoo, LM Nguyen, A van den Bosch – Computers in Industry, 2016 – Elsevier
… 26]. The tokens are then annotated with particular tags using named entity recognition, implemented with a sequential minimal optimization support vector machine (SMO SVM) [27] from the Weka machine learning library [28]. …

Higher-order Multivariable Polynomial Regression to Estimate Human Affective States
J Wei, T Chen, G Liu, J Yang – Scientific reports, 2016 – nature.com
… Starting from these observed signals, feature vectors are extracted, used to represent response patterns of different affective states, and classified into finite classes by using various classifiers (eg, support vector machine (SVM), artificial neural network (ANN), k-nearest …

Automatic recognition of negative emotion in speech using support vector machine
Y Yamamoto, M Niitsuma… – The Journal of the …, 2016 – asa.scitation.org
… Recognition of foreign-accented words in isolationMirrah Maziyah Mohamed, and Hayk Abrahamyan Oct 2016. Full Published Online: November 2016. Automatic recognition of negative emotion in speech using support vector machine. … in speech for speech dialogue system. …

Speaker Adaptation for Support Vector Machine based Word Prominence Detection
A Schnall, M Heckmann – Speech Prosody 2016, 2016 – pdfs.semanticscholar.org
Speaker Adaptation for Support Vector Machine based Word Prominence Detection … is getting more im- portant in human-machine communication, and integrating this information could improve the performance, prosody has been rarely used in spoken dialog systems so far [3, 4 …

Speech-based emotion recognition and speaker identification: static vs. dynamic mode of speech representation
M Sidorov, W Minker, ES Semenkin – … . ????? «?????????? ? ??????», 2016 – mathnet.ru
… SI and ER can be used to improve a Spoken Dialogue System (SDS). Furthermore, specific information about a speaker can lead to higher ER accuracy. Meanwhile there are many open questions in these fields. … Support Vector Machine (SVM). …

Emotion assessing using valence-arousal evaluation based on peripheral physiological signals and support vector machine
MBH Wiem, Z Lachiri – Control Engineering & Information …, 2016 – ieeexplore.ieee.org
… After preprocessing the signals, extracting and normalizing features, a support vector machine was applied to classify the emotional states into two classes … 200 I. [2] E. Andre, M. Rehm, W. Minker, and D. BUhler, “Endowing Spoken Language Dialogue Systems with Emotional …

Multi-label Topic Classification of Turkish Sentences Using Cascaded Approach for Dialog Management System
G So?anc?o?lu, B Köro?lu, O A??n – 2016 – tsdconference.org
… 7]. In this paper, we investigated topic classification problem that would be utilized in a Turkish dialogue system for banking domain. … C4.5, Naive Bayes, Support Vector Machine (SVM), Multilayer Perceptron (MLP) and Random Forest imple- mented in Weka1 were evaluated. …

Age driven automatic speech emotion recognition system
D Verma, D Mukhopadhyay – Computing, Communication and …, 2016 – ieeexplore.ieee.org
… Keywords—Speech emotion recognition, age recognition, prosodic features, spectral features, support vector machine … For example the automatic dialogue systems at the call centers equipped with emotion recognition capability can recognize the customer’s mood at the first …

Effective Korean Speech-act Classification Using the Classification Priority Application and a Post-correction Rules
N Song, K Bae, Y Ko – Journal of KIISE, 2016 – koreascience.or.kr
… act classification is important in a dialogue system. The machine learning and rule-based methods have mainly been used for speech-act classification. In this paper, we propose a speech-act classification method based on the combination of support vector machine (SVM) and …

Classification of Utterance Acceptability Based on BLEU Scores for Dialogue-Based CALL Systems
R Kuwa, X Wang, T Kato, S Yamamoto – International Conference on Text …, 2016 – Springer
… (3). Instead of using a support vector machine(SVM) as a classifier, we here used a … IEICE TRANS. Inf. Syst. 97(7), 1830–1841 (2014). 4. Raux, A., Eskenazi, M.: Using task-oriented spoken dialogue systems for language learning: potential, practical applications and challenges. …

A Deep Learning Methodology for Semantic Utterance Classification in Virtual Human Dialogue Systems
D Datta, V Brashers, J Owen, C White… – … Conference on Intelligent …, 2016 – Springer
… The majority of the work in dialogue systems relies on semantic utterance classification for the evaluation of natural language … Typically, these systems use supervised classification methods like boosting [10], support vector machine approaches [12] or maximum entropy models …

Application of a Hybrid Relation Extraction Framework for Intelligent Natural Language Processing
L Goel, R Khandelwal, E Retamino, S Nair… – … Symposium on Intelligent …, 2016 – Springer
… Hence in this work, a multiclass Support Vector Machine has been used where the classes are the different relations that can occur in the sentence. … Lee, CJ, Jung, SK, Kim, KD, Lee, DH, Lee, GGB (2010). Recent approaches to di- alog management for spoken dialog systems. …

Natural language dialog system considering speaker’s emotion for open-ended conversation
T Takahashi, K Mera, Y Kurosawa… – The Journal of the …, 2016 – asa.scitation.org
… dialog system that can estimate the user’s emotion from utterances and respond on the basis of the estimated emotion. To estimate a speaker’s emotion (positive, negative, or neutral), 384 acoustic features extracted from an utterance are utilized by a Support Vector Machine ( …

The MSIIP system for dialog state tracking challenge 5
Y Su, M Li, J Wu – Spoken Language Technology Workshop …, 2016 – ieeexplore.ieee.org
… Support Vector Machine (SVM) is used as basic classification model. … 21, no. 2, pp. 393–422, 2007. [2] Blaise Thomson and Steve Young, “Bayesian update of dialogue state: A pomdp framework for spoken dialogue systems,” Computer Speech & Language, vol. 24, no. 4, pp. …

Towards the detection of learner’s uncertainty through face
SAA Daud, SL Lutfi – User Science and Engineering (i-USEr) …, 2016 – ieeexplore.ieee.org
… 1976. [9] AA Abdullah. Automatic and Person-Independent Detection of 3D Facial Expressions Using Enhanced Support Vector Machine with Probability Estimation. IEEE Digital Library. … In Perception in Multimodal Dialogue Systems (pp. 221-232). Springer Berlin Heidelberg. …

Backchanneling via Twitter Data for Conversational Dialogue Systems
M Inaba, K Takahashi – International Conference on Speech and …, 2016 – Springer
… Given the above issues, in this study, we propose a method for generating a rich variety of backchanneling to realize smooth communication in conversational dialogue systems. … Baseline 2: Multi-class Support Vector Machine. …

From Dialogue Corpora to Dialogue Systems: Generating a Chatbot with Teenager Personality for Preventing Cyber-Pedophilia
Á Callejas-Rodríguez, E Villatoro-Tello, I Meza… – … Conference on Text …, 2016 – Springer
… Section 2 present some related work concerning to the SPI problem and automatic dialogue systems. In Sect. … Recently, in [4] authors proposed a semi-supervised approach called one-class Support Vector Machine algorithm for anomaly detection of on-line predators. …

Feature-Level Decision Fusion for Audio-Visual Word Prominence Detection.
M Heckmann – INTERSPEECH, 2016 – pdfs.semanticscholar.org
… These functionals then serve as features for a Support Vector Machine (SVM) based classifier. 4.1. … INTERSPEECH. Portland, OR: ISCA, 2012. [12] M. Swerts, D. Litman, and J. Hirschberg, “Corrections in spoken dialogue systems,” in Sixth Int. Conf. on Spoken Language Proc. …

MULTI-OBJECTIVE GENETIC ALGORITHMS AS AN EFFECTIVE TOOL FOR FEATURE SELECTION IN THE SPEECH-BASED EMOTION RECOGNITION …
CY Brester, OE Semenkina, MY Sidorov – christinabrester.com
… multi-objective genetic algorithms (MOGAs) and their modifications are used as optimizers; a Multilayer Perceptron, a Support Vector Machine and Logistic … One of the obvious ways to improve the intellectual abilities of spoken dialogue systems is related to their personalization. …

MULTI-CRITERIA SELF-ADJUSTING GENETIC PROGRAMMING FOR DESIGN NEURAL NETWORK MODELS IN THE TASK OF FEATURE SELECTION
E Loseva – ??????????? ???? ??????, 2016 – elibrary.ru
… The main difficulty for good working dialog systems lies in the processing of large amounts of data … For comparison the effectiveness on the «full» and «shortened» sets of features the following classifiers were chosen: – Support Vector Machine – SVM, which was used for training …

Speech Intent Recognition for Robots
B Shen, D Inkpen – … and Computers in Sciences and in Industry …, 2016 – ieeexplore.ieee.org
… D. Spoken Language Understanding The Spoken Language Understanding (SLU) module is the processing module of the dialog system. … by using bag of words (BOW) and verb relevance as features, and the classification is done by a Support Vector Machine (SVM) classifier. …

Estimating the User’s State before Exchanging Utterances Using Intermediate Acoustic Features for Spoken Dialog Systems.
Y Chiba, T Nose, M Ito, A Ito – IAENG International Journal of Computer …, 2016 – iaeng.org
… WOZ method, as much natural dialog data as possible is collected by having the user converse with a simulated dialog system. … C. Experimental conditions for discriminating the user’s state The user’s state was discriminated by the Support Vector Machine (SVM) with RBF kernel …

An English-Arabic Real Time System (EARS)
AA Sakr – International Journal – pdfs.semanticscholar.org
… Viterbi is applied in dialogue systems, where desired semantic output is more clear. … on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and Summarization, Ann Arbor, (2015) 19-H. Shi and Y. Liu, Naïve Bayes versus Support Vector Machine, Resillience to …

A Unified Knowledge Representation System for Robot Learning and Dialogue
N Shukla – 2016 – search.proquest.com
… On top of that, we train a shirt detector model using a Support Vector Machine to facilitate narrowing down the search for an optimal S-AoG parse graph. … Collaborative activities and multi-tasking in dialogue systems: Towards natural dialogue with robots. TAL. …

Performance of Multimodal Biometric System Based on Level and Method of Fusion
M Pathak, N Srinivasu – Advances in Computing Applications, 2016 – Springer
… Domains such as sports video analysis and multimodal dialog system mostly use rule-based fusion method. … Methods for classifications are support vector machine (SVM), Bayesian interface, dynamic Bayesian network (DBN), neural network (NN), Dempster–Shafer theory and …

Could Speaker, Gender or Age Awareness be beneficial in Speech-based Emotion Recognition?
M Sidorov, A Schmitt, E Semenkin, W Minker – LREC, 2016 – lrec-conf.org
… important part of dialogue analysis which can be used in order to improve the quality of Spoken Dialogue Systems (SDSs … of classification algorithms, namely k-Nearest Neighbours (KNN) (Cover and Hart, 1967), Multi-Layer Perceptron (MLP), Support Vector Machine (SVM) (Xue …

Sentiment-subjective analysis framework for arabic social media posts
NFB Hathlian, AM Hafezs – Information Technology (Big Data …, 2016 – ieeexplore.ieee.org
… considered for a comparative study over a given dataset, we have tested both the Naive Bayes Classifier (NBC) and the Support Vector Machine (SVM), which … 16] M. Hijjawi et al., “An Arabic Stemming approach using machine learning with Arabic dialogue system,” ICGST AIML …

Text classification for spoken dialogue systems
R Sergienko – 2016 – oparu.uni-ulm.de
… 2.1. Spoken Dialogue Systems…………… 17 2.2. Text Classification Applied for Spoken Dialogue Systems…………… 19 2.3. … Self-adjusting genetic algorithm 2.14. Support vector machine 4.1. Numerical results with all terms for data configuration 1 …

Multiple optima identification using multi-strategy multimodal genetic algorithm
EA Sopov – … of Siberian Federal University. Mathematics & …, 2016 – search.proquest.com
… Topic categorization of users’ utterances can be also useful for multi-domain spoken dialogue system design [2]. In this work we … After text preprocessing, machine learning algorithms are applied for the classification, such as k -NN, support vector machine (SVM) [11], Rocchio …

Manga content analysis using physiological signals
CL Sanches, O Augereau, K Kise – … of the 1st International Workshop on …, 2016 – dl.acm.org
… 4.1 Classification method In order to know which is the corresponding manga for each 20 second window we use a Support Vector Machine (SVM) classification method. … In Tutorial and research workshop on affective dialogue systems, pages 36–48. Springer, 2004. …

Multi-objective genetic algorithms as an effective tool for feature selection in the speech-based emotion recognition problem
BC Yu, OE Semenkina, MY Sidorov – … ???????????? ??. ????????? …, 2016 – cyberleninka.ru
… multi-objective genetic algorithms (MOGAs) and their modifications are used as optimizers; a Multilayer Perceptron, a Support Vector Machine and Logistic … One of the obvious ways to improve the intellectual abilities of spoken dialogue systems is related to their personalization. …

Enhanced Spoken Sentence Retrieval Using a Conventional Automatic Speech Recognizer in Smart Home
H Ahn, H Kim – International Journal on Artificial Intelligence Tools, 2016 – World Scientific
… The re-ranking model rearranges top-n outputs of the ASR engines using the ranking support vector machine (Ranking SVM). … 2137– 2140. 8. J. Choi, D. Lee, S. Ryu, K. Lee and GG Lee, Engine-independent ASR error management for dialog systems, in Proc. …

Personalized Natural Language Understanding.
X Liu, R Sarikaya, L Zhao, Y Ni, YC Pan – INTERSPEECH, 2016 – pdfs.semanticscholar.org
… as a means to enable information access, task completion, and ultimately to improve user’s productivity [1]. The dialog system on PDAs … Typically, a machine learned classifier such as multi-class support vector machine (SVM) or deep learning models are built for both domain …

Urdu speech recognition system for district names of Pakistan: Development, challenges and solutions
M Qasim, S Nawaz, S Hussain… – … and Standardization of …, 2016 – ieeexplore.ieee.org
… The system is developed for use in a spoken dialog system that provides weather information to the citizens of Pakistan in … Three approaches were used to classify different accents: 1) using Support Vector Machine (SVM) and Random Forest, 2) using Gaussian Mixture Models …

A review study of human-affection knowledge on usability engineering
D Lakshmi, R Ponnusamy – Advances in Human Machine …, 2016 – ieeexplore.ieee.org
… EMG signals are recorded by means of an electrode placed on the first dorsal interosseous muscle and processed by a Support Vector Machine(SVM) using … [50] Alonso-Martín, F.; Castro-González, A.; Luengo, F.; Salichs, M. Augmented Robotics Dialog System for Enhancing …

Spoken Language Understanding for Service Robotics in Italian
D Nardi – AI* IA 2016 Advances in Artificial Intelligence: XVth …, 2016 – books.google.com
… Spoken Language Understanding (SLU) for interactive dialogue systems acquires a specific nature when applied to Interactive Robotics. … This module is realized through a learn-to-rank app- roach, where a Support Vector Machine exploiting a combination of linguistic kernels is …

Automatic Detection of Hyperarticulated Speech
E Ribeiro, F Batista, I Trancoso, R Ribeiro… – Advances in Speech …, 2016 – Springer
… Automatic detection of hyperarticulated speech is important because if a dialog system is able to do so, it can try to recognize the … The automatic detection approach consists of a Support Vector Machine (SVM) classifier trained using Let’s Go [14] data from the years of 2009 and …

Targeted Sentiment Analysis: Identifying Student Sentiment Toward Courses and Instructors
C Welch, R Mihalcea – workshop.colips.org
… The time, tl that the opinion is expressed would also be apparent in timestamped interactions with the dialog system. … The second highest scoring system used a support vector machine (SVM) classifier with features derived from n-grams, point- wise mutual information scores …

A survey of semantic similarity measuring techniques for information retrieval
M Kathuria, CK Nagpal, N Duhan – Computing for Sustainable …, 2016 – ieeexplore.ieee.org
… proceSSing taSkS Such aS language modeling, word SenSe diSamBiguation, grammar induction, Speech underStanding and open dialogue SyStem. … meaSurement index uSing a page count, text Snippet and training of patternS uSing Support Vector machine (SVm) to …

Adapting Spoken Dialog Systems Towards Domains and Users
M Sun – 2016 – lti.cs.cmu.edu
Page 1. Adapting Spoken Dialog Systems Towards Domains and Users Ming Sun CMU-LTI-16-006 … c 2016 , Ming Sun Page 2. Keywords: Lexicon learning, cloud speech recognition adaptation, high-level intention un- derstanding, spoken dialog systems Page 3. Abstract …

Annotation and analysis of listener’s engagement based on multi-modal behaviors
K Inoue, D Lala, S Nakamura, K Takanashi… – Proceedings of the …, 2016 – dl.acm.org
… This data was used to learn a support vector machine to detect the engagement intention from visual information. A few studies have been conducted using human-human conversation data. … Knowledge graph inference for spoken dialog systems. In Proc. …

Deep Learning+ Student Modeling+ Clustering: a Recipe for Effective Automatic Short Answer Grading.
Y Zhang, R Shah, M Chi – EDM, 2016 – pdfs.semanticscholar.org
… Prior research on ASAG successfully explored several clas- sic ML methods which included: Naive Bayes (NB), Logistic Regression (LR), Decision Tree (DT), Artificial Neutral Net- work (ANN), and Support Vector Machine (SVM). … Beetle ii: an adaptable tutorial dialogue system. …

Study on Optimal Spoken Dialogue System for Robust Information Search in the Real World
?? – 2016 – eprints.lib.hokudai.ac.jp
… Page 29. Chapter 2. Key Technologies of Spoken Dialogue Systems and Related Works 16 duration of the longest voiced speech. … With the extracted features, GMM and support vector machine (SVM) are mainly used to correctly classify the emotion. …

A generalized framework for anaphora resolution in Indian languages
UK Sikdar, A Ekbal, S Saha – Knowledge-Based Systems, 2016 – Elsevier
… Keywords. Multiobjective optimization (MOO); Single objective optimization (SOO); Conditional random field (CRF); Support vector machine (SVM). 1. Introduction. … As machine learner we use Conditional Random Field (CRF) [17] and Support Vector Machine (SVM)[41]. …

A Supervised Learning Approach for the Fusion of Multiple Classifier Outputs
C Ulas, B Koroglu, C Bekar, O Burcak, O Agin – 2016 – ijsps.com
… Empirically we also attempted to utilize Support Vector Machine (SVM) to compare the performance. … She has been working on numerous industrial applications on noisy text classification, short-text clustering and human-computer dialogue systems. …

Combination of Empirical Mode Decomposition Components of HRV Signals for Discriminating Emotional States
A Goshvarpour, A Abbasi… – Iranian Journal of Medical …, 2016 – ijmp.mums.ac.ir
… adopted a support vector machine (SVM) as a classifier for the discrimination of emotions in 50 subjects [2]. By applying linear and spectral features, maximum correct rates of 78.4% and 61.8% were reported for the recognition of three and four affective states, respectively. …

Training an interactive humanoid robot using multimodal deep reinforcement learning
H Cuayáhuitl, G Couly, C Olalainty – arXiv preprint arXiv:1611.08666, 2016 – arxiv.org
… layer with 8 filters, RELU, pooling layer of size 2×2 with stride 2, convolutional layer with 16 filters, RELU, pooling layer of size 3×3 with stride 3, and the output layer used a Support Vector Machine (SVM) with 3 … SimpleDS: A simple deep reinforcement learning dialogue system. …

An Empirical Investigation of Word Clustering Techniques for Natural Language Understanding
DA Shunmugam, P Archana – International Journal of Engineering …, 2016 – ijesc.org
… Logistic Regression, Boosting, Support Vector Machine (SVM) are commonly used predictive learning domain classification and intent classification tasks and … first set is internally collected multimedia data from live deployment scenarios of a spoken dialog system designed for …

Robust comprehension of natural language instructions by a domestic service robot
T Kobori, T Nakamura, M Nakano, T Nagai… – Advanced …, 2016 – Taylor & Francis
… The proposed method combines action-type classification, which is based on a support vector machine, and slot extraction, which is based on conditional random fields, both of which are required in order for a robot to execute an action. …

MobileSSI-A Multi-modal Framework for Social Signal Interpretation on Mobile Devices
S Flutura, J Wagner, F Lingenfelser… – … (IE), 2016 12th …, 2016 – ieeexplore.ieee.org
… RESULTS AND DISCUSSION As in our previous study [5], we trained a Support Vector Machine (SVM) classifier for each modality and used leave- one-user-out for evaluation, calculating an average … In Perception in Multimodal Dialogue Systems, volume 5078, pages 188–199 …

The splab at the NTCIR-12 Short Text Conversation Task.
K Wu, X Liu, K Yu – NTCIR, 2016 – pdfs.semanticscholar.org
… In the subtask, we build a single round of retrival-based dialogue system based on a repository of weibo data, which is provided by the … In the SVM ranking module, we use the ranking SVM [7] by Thorsten Joachims, which is an variant of the support vector machine algorithm. …

Perceptually informed spoken language understanding for service robotics
E Bastianelli, D Croce, A Vanzo… – Proceedings of the …, 2016 – sag.art.uniroma2.it
… Spoken Language Understanding (SLU) for interactive dialogue systems acquires a specific nature, when applied in Interactive Robotics … Re-ranking is performed using a learn-to-rank ap- proach, where a Support Vector Machine exploiting a com- bination of linguistic kernels is …

Providing arguments in discussions on the basis of the prediction of human argumentative behavior
A Rosenfeld, S Kraus – ACM Transactions on Interactive Intelligent …, 2016 – dl.acm.org
… An agent can help a user in this task by revealing additional 3Also known as dialog systems. ACM Transactions on Interactive Intelligent Systems, Vol. 6, No. 4, Article 30, Publication date: December 2016. Page 6. 30:6 A. Rosenfeld and S. Kraus …

Determining speaker attributes from stress-affected speech in emergency situations with hybrid SVM-DNN architecture
J Ahmad, M Sajjad, S Rho, S Kwon, MY Lee… – Multimedia Tools and …, 2016 – Springer
… growing applications in communication, human-computer inter- action (HCI), telephone speech forensic analysis, and natural language dialog systems. … Support vector machine has recently been adopted for speaker recognition tasks due to its better generalization capabilities. …

Extraction of sparse features of color images in recognizing objects
TTQ Bui, TT Vu, KS Hong – International Journal of Control …, 2016 – search.proquest.com
… 40] GM Lim, DM Bae, and JH Kim, Fault diagnosis of rotating machine by thermography method on support vector machine, Journal of Mechanical Science and Technology, vol. … His research interests include language understanding, computer vision, dialog system, and robotics …

An Overview of Feature Based Opinion Mining
A Golande, R Kamble, S Waghere – The International Symposium on …, 2016 – Springer
… For the sentiment classification task Support Vector Machine (SVM) classifier was used. … Newton, MA, USA: O’Reilly, 2011. [30] Z. Callejas and R. Lopez_-Cozar,_ “Influence of contextual informa-tion in emotion annotation for spoken dialogue systems,” Speech Commun., vol. …

A Naïve Bays Classifier to Classify Movie
N Raghuvanshi, JM Patil – ijarcet.org
… movies, politicians, etc., improving customer relation models, detecting happiness and well-being, and improving automatic dialogue systems. … 2006), machine learning algorithms, such as Naive Bayes (NB), Maximum Entropy (ME), Support Vector Machine (SVM) (Joachims …

Prediction of Deception and Sincerity from Speech Using Automatic Phone Recognition-Based Features.
R Herms – INTERSPEECH, 2016 – researchgate.net
… The prediction of deception, as a classification task, was performed using support vector machine (SVM) with a lin- ear kernel function. … [11] J. Tepperman, DR Traum, and S. Narayanan, “” yeah right”: sarcasm recognition for spoken dialogue systems.” in INTER- SPEECH, 2006. …

Prototype-based class-specific nonlinear subspace learning for large-scale face verification
A Iosifidis, M Gabbouj – … Tools and Applications (IPTA), 2016 6th …, 2016 – ieeexplore.ieee.org
… ing Machine (ELM) [20], Reduced Kernel Support Vector Machine (RKSVM) [16], Approximate Kernel Extreme Learn- ing Machine (AKELM) [19], Random Feature Regression (RFR) [31], using the same feature space dimensionality or reference vector set cardinality. …

Effects of emotion on physiological signals
S Basu, A Bag, M Aftabuddin… – … ), 2016 IEEE Annual, 2016 – ieeexplore.ieee.org
… E. Classification Depending upon nature of experiment, available data and expected outcome, various classifiers can be used, for example Regression Tree, Bayesian Networks, k Nearest Neighbour (kNN) [15] [32], Support Vector Machine (SVM) [15][23], Artificial Neural …

Emotional arousal estimation while reading comics based on physiological signal analysis
M Matsubara, O Augereau, CL Sanches… – Proceedings of the 1st …, 2016 – dl.acm.org
… This setup can easily be applied in every day life environment. The proposed method extracts features from the signals and applies the support vector machine (SVM) to estimate the arousal. … In Tutorial and research workshop on affective dialogue systems, pages 36–48. …

Overview of NTCIR-12.
K Kishida, MP Kato – NTCIR, 2016 – research.nii.ac.jp
… Then, we construct the classification model based on support vector machine (SVM) in order to solve the question of choosing right or wrong sentence in multiple choice-type questions for the National Center Test; we extract five features about questions and choices as inputs to …

Multilingual Spoken Language Understanding using graphs and multiple translations
M Calvo, LF Hurtado, F Garcia, E Sanchis… – Computer Speech & …, 2016 – Elsevier
… We have applied this approach to the SLU module of a Spoken Dialog System for the DIHANA task (Benedí et al., 2006), which consists of an information system about train timetables and fares in Spanish. … (2012), an application of Support Vector Machine (SVM) classifiers to …

Towards Natural Human Control and Navigation of Autonomous Wheelchairs
S Echefu – 2016 – search.proquest.com
… These spikes are removed by setting those random array values to neighboring entries in the array. Each particle location is passed into a multi-class Support Vector Machine (SVM) classifier which gives the probability of n class locations and poses. …

SpaceRef: A corpus of street-level geographic descriptions.
J Götze, J Boye – LREC, 2016 – lrec-conf.org
… A geographical spoken dialogue system must be able to both interpret and generate utter- ances containing references to real-world objects in … We trained a Support Vector Machine model that ranks all objects in the near vicinity ac- cording to these user preferences, and found …

Emotion extraction based on multi bio-signal using back-propagation neural network
G Yoo, S Seo, S Hong, H Kim – Multimedia Tools and Applications, 2016 – Springer
… machine learning algorithms, such as Sequential Floating Forward Search, k-Nearest Neighbor (k-NN) algorithm, Support Vector Machine (SVM), and … 2004) Emotion recognition using bio-sensors: first step towards an automatic system, in affective dialogue systems tutorial and …

Institute of Communications Engineering Staff
M Bossert, R Fischer, W Minker, UC Fiebig… – Journal of Siberian …, 2016 – uni-ulm.de
… algorithms for support vector machine automated design International Conference on Engineering and Applied Sciences Optimization (OPT-i), Kos Island, Greece, June 2014 Bibtex. S. Ultes and W. Minker Interaction Quality Estimation in Spoken Dialogue Systems Using Hybrid …

Towards Building an Attentive Artificial Listener
C Oertel, J Lopes, Y Yu, KAF Mora, J Gustafson… – idiap.ch
… 8], who uses backchannels as one strategy for establishing rapport between a human and a virtual human, or [22], who used backchannels in their dialogue system to study turn … In our experiments we used a Support Vector Machine (SVM) classifier based on the linear kernel. …

Technology for Soccer Sport: The Human Side in the Technical Part
L Varriale, D Tafuri – International Conference on Exploring Services …, 2016 – Springer
… models to automatically detect event in soccer sport; hence, numerous machine learning algorithms were broadly applied, such as Dynamic Bayesian Network (DBN) model, Hidden Markov Model (HMM), Conditional Random Fields model, Support Vector Machine (SVM) model …

TROPE
TBAN ATTENTIVE, A LISTENER – 2016 – pdfs.semanticscholar.org
… 6], who uses backchannels as one strategy for establishing rapport between a human and a virtual human, or [16], who used backchannels in their dialogue system to study turn … In our experiments we used a Support Vector Machine (SVM) classifier based on the linear kernel. …

Institute of Information Technology
J Lindner, W Teich, A Linduska, M Mostafa… – Journal of Siberian …, 2016 – uni-ulm.de
… algorithms for support vector machine automated design International Conference on Engineering and Applied Sciences Optimization (OPT-i), Kos Island, Greece, June 2014 Bibtex. S. Ultes and W. Minker Interaction Quality Estimation in Spoken Dialogue Systems Using Hybrid …

A Review on Deep Learning Algorithms for Speech and Facial Emotion Recognition
CP Latha, M Priya – APTIKOM Journal on Computer Science …, 2016 – jurnal.aptikom.or.id
… After all the layers in the stacked auto encoder is trained, the output can be used as an input to any supervised learning algorithms like Support Vector Machine, Multiclass logistic regression etc. Figure 5 represents the diagram of a stacked auto encoder. …

Data-driven deep-syntactic dependency parsing
M Ballesteros, B Bohnet, S Mille… – Natural Language …, 2016 – cambridge.org
Page 1. Natural Language Engineering 22 (6): 939–974. c Cambridge University Press 2015 doi:10.1017/S1351324915000285 939 Data-driven deep-syntactic dependency parsing† MIGUEL BALLESTEROS1, BERND BOHNET2 …

Detecting paralinguistic events in audio stream using context in features and probabilistic decisions
R Gupta, K Audhkhasi, S Lee, S Narayanan – Computer Speech & …, 2016 – Elsevier
Non-verbal communication involves encoding, transmission and decoding of non-lexical cues and is realized using vocal (eg prosody) or visual (eg gaze, body.

Determination of Emotional State through Physiological Measurement
LB Hinkle – 2016 – digital.library.txstate.edu
… RIP Respiratory Inductance Plethysmography SKT Skin Temperature SpO2 Oxygen saturation of arterial hemoglobin SVM Support Vector Machine Page 13. xiii ABSTRACT The goal of this thesis is to develop and evaluate methods of emotional response …

Detecting affective states from text based on a multi-component emotion model
Y Gao, W Zhu – Computer Speech & Language, 2016 – Elsevier
… Therefore, the machine learning method is selected to implement the detecting work. The classifiers such as Support Vector Machine (SVM) and Maximum Entropy (ME) are the commonly used machine learning techniques in the emotion detection task. …

Analysis and estimation of driver visual attention using head position and orientation in naturalistic driving conditions
S Jha – 2016 – search.proquest.com
… prole. Then, geometric facial features are used to train a support vector machine (SVM) that classify gaze into eight predeterminate areas. … 2013). It can also play an important role in in-vehicle situated dialog systems (Misu, 2015). …

Construction and analysis of phonetically and prosodically balanced emotional speech database
E Takeishi, T Nose, Y Chiba, A Ito – … and Standardization of …, 2016 – ieeexplore.ieee.org
… Therefore, an automatic spoken dialogue system can make a conversation with good impression by recognizing the interlocutor’s … recognition using SVM We evaluated effectiveness of emotion recognition by automatic emotional classification using the Support Vector Machine. …

A pattern-Based approach for Sarcasm Detection on Twitter
M Bouazizi, TO Ohtsuki – IEEE Access, 2016 – ieeexplore.ieee.org
… newswire documents. They introduced a set of features including the use of profanity and slangs and what they qualified of ”semantic validity”; and used Support Vector Machine (SVM) classifier to recognize satire articles. Campbell …

The conversational interface
M McTear, Z Callejas, D Griol – New York: Springer, 2016 – Springer
… With the evolution of speech recognition and natural language technologies, IVR systems rapidly became more sophisticated and enabled the creation of complex dialog systems that could handle natural language queries and many turns of interaction. …

Recognition System for Home-Service-Related Sign Language Using Entropy-Based -Means Algorithm and ABC-Based HMM
THS Li, MC Kao, PH Kuo – IEEE Transactions on Systems, Man …, 2016 – ieeexplore.ieee.org
… model. Reference [33] indicated a hierarchi- cal change detection test, which coupled with K Nearest Neighbor (KNN) and Support Vector Machine (SVM), is an appropriate tool for processing and classifying sequential data. …

Prominent feature extraction for sentiment analysis
B Agarwal, N Mittal – 2016 – Springer
… of affect (facial expressions, posture, behavior, physiology), and affective interfaces and applications (dialogue systems, games, learning etc … BMNB) machine learning algorithm with mRMR feature selection technique performs better than Support Vector Machine (SVM) classifier …

Affective analysis and Modeling of Spoken Dialogue Transcripts
E Palogiannidi – 2016 – researchgate.net
… Jose Lopes, Arodami Chorianopoulou, Elisavet Palogiannidi, Helena Moniz, Alberto Abad, Katerina Louka, Elias Iosif and Aleandros Potamianos “The SpeDial Datasets: Datasets for Spoken Dialogue Systems Analytics”, in Proceedings of the 10th edition of the Language …

A novel approach to improve the planning of adaptive and interactive sessions for the treatment of Major Depression
A Bresó, J Martínez-Miranda, E Fuster-García… – International Journal of …, 2016 – Elsevier
… historical interactions. Fukazawa et al. (2009) proposed and evaluated a method that ranks (using Ranking SVM -Support Vector Machine-) the menu functions of a mobile application based on user operation history. Bae et al. (2014 …

Large Scale Data Enabled Evolution of Spoken Language Research and Applications
S Jothilakshmi, VN Gudivada – Handbook of Statistics, 2016 – Elsevier
Natural Language Processing (NLP) is an interdisciplinary field whose goal is to analyze and understand human languages. Natural languages are used in two forms.

Situated Intelligent Interactive Systems
Z Yu – 2016 – cs.cmu.edu
… Page 3. Abstract The recent wide usage of Interactive Systems (or Dialog Systems), such as Apple Siri has at- tracted a lot of attention. The ultimate goal is to transform current systems into real intelligent … 14 4 TickTock, A Non-Task-Oriented Dialog System Framework 15 …

Leveraging biometric data to boost software developer productivity
T Fritz, SC Müller – Software Analysis, Evolution, and …, 2016 – ieeexplore.ieee.org
… fine-grained five state classification. For the machine learning we used Na?ve Bayes since it outperformed Decision Trees and Support Vector Machine approaches with a ten-fold cross-validation. Findings. For the lab as well …

Analysis, optimization and development of an answer scoring system
I Lopez-Gazpio – 2016 – addi.ehu.es
… 7 sponse classes1. The corpora has been created out of two established sources: the BEETLE corpus, a data set collected and annotated during the evalu- ation of the BEETLE II tutorial dialogue system [Dzikovska et al., 2010]; and the SCIENTSBANK corpus, a set of student …

Giving eyesight to the blind: Towards attention-aware AIED
SK D’Mello – International Journal of Artificial Intelligence in …, 2016 – Springer
… example, the use of the learner’s first name (eg, “Mary, what do you think about this problem”) in spoken dialog systems should be … A support vector machine was used to discriminate between mind wandering (pages with a self-report—32 %) and normal reading from eye-gaze …

Prediction of Who Will Be the Next Speaker and When Using Gaze Behavior in Multiparty Meetings
R Ishii, K Otsuka, S Kumano, J Yamato – ACM Transactions on …, 2016 – dl.acm.org
… The results of subjective evaluations of the dialogue system suggest that interactions with a system using their model are perceived as … The model is based on a support vector machine (SVM), in which the method is Sequential Minimal Optimization (SMO) [Keerthi et al. …

Sentiment analysis: from opinion mining to human-agent interaction
C Clavel, Z Callejas – IEEE Transactions on affective computing, 2016 – ieeexplore.ieee.org
… Detection and avoidance of user frustration in driving situations [77] or for tutoring systems [78] or for a child conversational computer game [83]. Detection of various emotions according to the application for dialog systems [25], [81], [83]. …

Detecting Sarcasm in Multimodal Social Platforms
R Schifanella, P de Juan, J Tetreault… – Proceedings of the 2016 …, 2016 – dl.acm.org
… YFCC100M. Each concept classifier is a binary support vector machine, for which positive examples were manually labeled based on targeted search/group results, while the negatives drew negative examples from a general pool. …

Automatic detection of Parkinson’s disease in running speech spoken in three different languages
JR Orozco-Arroyave, F Hönig… – The Journal of the …, 2016 – asa.scitation.org

Modeling Satire in English Text for Automatic Detection
AN Reganti, T Maheshwari, U Kumar… – … (ICDMW), 2016 IEEE …, 2016 – ieeexplore.ieee.org
… The Scikit- Learn package in python was used to evaluate the results. Five different classifiers have been used, Logistic Regression (LR), Random Forest (RF), Support Vector Machine (SVM), Decision Tree (DT) and an ensemble of classifiers for better performance. …

STRESS RECOGNITION FROM SPEECH SIGNAL
M STAN?K – vutbr.cz
… OSALPCC Cepstral-based OSALPC SVM Support Vector Machine TEO Teager Energy Operator TTB Top-To-Bottom Page 8. … 65 Fig. 46 Accuracy of stress detection depending on selected n-percentage interval and using Support Vector Machine as a classifier. …

Statistical analysis of multivariate data in bioinformatics
T Metsalu – 2016 – dspace.ut.ee
… 33 3.2.3 Support vector machine . . . . . … VI reanalyzed public gene expression data and wrote materials and methods for this part. VI I created support vector machine classifier for clinical score formula and wrote methods part about it. 8 Page 9. ABSTRACT …

Towards next-generation visual archives: i mage, film and discourse
J Bateman, CI Tseng, O Seizov, A Jacobs, A Lüdtke… – Visual …, 2016 – Taylor & Francis
… on the application of functional linguistic and corpus methods to multimodal meaning making, analysing and critiquing multimodal documents of all kinds, the development of linguistically motivated ontologies and the construction of computational dialogue systems for robot …

Highly Pertinent Algorithm for the Market of Business Intelligence, Context and Native Advertising
AI Guseva, VS Kireev… – International Journal of …, 2016 – search.proquest.com
… In dialogue systems, ie, the systems supporting interactive process, more advanced models of transaction … The support vector machine (SVM) method is a set of similar learning algorithms with the teacher, used for the classication problems and regression analysis (Krivenko and …

Emotion Identification from Spontaneous Communication
MK Dorry – 2016 – etd.aau.edu.et
Page 1. Addis Ababa University College of Natural Sciences Emotion Identification from Spontaneous Communication Mikiyas Kebede Dorry A Thesis Submitted to the Department of Computer Science in Partial Fulfilment for the Degree of Master of Science in …

D4. 7 1st Expressive Virtual Characters
F Yang, C Peters – 2016 – prosociallearn.eu
… interaction 1 . The SEMAINE project 2 built a Sensitive Artificial Listener (SAL) and a multimodal dialogue system which can react to the user’s verbal and non-verbal behavior and sustain the interaction for a long time. Greta …

Towards building a review recommendation system that trains novices by leveraging the actions of experts
S Khanal – 2016 – digitalcommons.unl.edu
Page 1. University of Nebraska – Lincoln DigitalCommons@University of Nebraska – Lincoln …

DeepLibrary: Wrapper Library for DeepDesign
J Ebbe – 2016 – e-collection.library.ethz.ch
… Another wrapper maintenance method is EDG-WM [13], which consists out of three steps. In a first step, a support vector machine is trained using previously correctly extracted data. To do so, attributes, position, font, color, size and path are used as features to describe the data. …

Intelligent Robotics and Applications: 9th International Conference, ICIRA 2016, Tokyo, Japan, August 22-24, 2016, Proceedings
N Kubota, K Kiguchi, H Liu, T Obo – 2016 – books.google.com
Page 1. Naoyuki Kubota · Kazuo Kiguchi Honghai Liu · Takenori Obo (Eds.) Intelligent Robotics and Applications 9th International Conference, ICIRA 2016 Tokyo, Japan, August 22–24, 2016 Proceedings, Part II 123 Page 2. …

A data-driven approach to automatic tweet generation about traffic incidents
MK Tran – 2016 – summit.sfu.ca
… The MATCH dialogue system [12, 45] is an NLG system that gives users restaurant rec- ommendations … The hash-tags are also generated automatically using a Support Vector Machine model in order to address the topic of the original document for easily grouping and searching …

Emotion Recognition from Speech with Acoustic, Non-Linear and Wavelet-based Features Extracted in Different Acoustic Conditions
JC Vásquez Correa – 2016 – bibliotecadigital.udea.edu.co
… Page 20. 2 Introduction efforts are devoted to increasing accessibility and efficiency of spoken dialogue systems by integrating emotional and other paralinguistic cues [2]. … the seven emotions in the Berlin database. A support vector machine (SVM) with a Gaussian …

Power Data Classification: A Hybrid of a Novel Local Time Warping and LSTM
Y Li, H Hu, Y Wen, J Zhang – arXiv preprint arXiv:1608.04171, 2016 – arxiv.org
… For this problem, common classifiers like support vector machine (SVM), k-nearest neighbour (KNN) with Euclidean distance have been proved to be non-competitive to the DTW distance measurement based method like 1NN-DTW [13]. Recently there have been a lot of new …

Introduction to EEG-and Speech-based Emotion Recognition
PA Abhang, BW Gawali, SC Mehrotra – 2016 – books.google.com
Page 1. introduction to EEG- and Speech-Based Emotion Recognition | Priyanka A. Abhang, Bhart W. Gawali, and Suresh C. Mehrotra . mill || || “li ? M “M Page 2. INTRODUCTION TO EEG- AND SPEECH-BASED EMOTION RECOGNITION Page 3. This page intentionally left blank …

Incremental Learning from Scratch Using Analogical Reasoning
V Letard, S Rosset, G Illouz – Tools with Artificial Intelligence …, 2016 – ieeexplore.ieee.org
Page 1. Incremental Learning From Scratch Using Analogical Reasoning Vincent Letard1,2,3, Sophie Rosset1 and Gabriel Illouz1,2,3 1LIMSI CNRS, France 2Université Paris Sud, France 3Université Paris Saclay, France firstname.lastname@limsi.fr …

Machine Learning: The New AI
E Alpaydin – 2016 – books.google.com
Page 1. MACHINE LEARNING ETHEM ALPAYDIN O 1 000 1 0 1 0 1 1 1 0 1 000 1 1 0 1 000 O 1 1 00 1 0 1 0 1 1 0 1 1 0 1 00 1 00000 O 1 00000 1 0 1 1 0 1 1 000 1 1 1 0000 O 1 1 0000 1 0 1 1 1 1 00 1 0 1 1 00 1 00 O 1 1 0 …

Energy-scalable speech recognition circuits
M Price – 2016 – dspace.mit.edu
… 20 Page 21. SRAM static random-access memory STFT short-term Fourier transform STL Standard Template Library SV SystemVerilog SVD singular value decomposition SVM support vector machine … In dialogue systems, the …

A data mining approach to ontology learning for automatic content-related question-answering in MOOCs.
S Shatnawi – 2016 – openair.rgu.ac.uk
Page 1. AUTHOR: TITLE: YEAR: OpenAIR citation: OpenAIR takedown statement: This work is made freely available under open access. This ?????? is distributed under a CC _____ license. _____ …

Incrementally resolving references in order to identify visually present objects in a situated dialogue setting
C Kennington – 2016 – pub.uni-bielefeld.de
… The practical goal of such a model is for it to be implemented as a component for use in a live, interactive, autonomous spoken dialogue system. … Page 4. 4 Acknowledgements Upon arrival at Bielefeld, my knowledge about dialogue systems research was impoverished at best. …

Review on using physiology in quality of experience
S Arndt, K Brunnström, E Cheng, U Engelke… – Electronic …, 2016 – ingentaconnect.com
… The data shows a stronger P300 peak for the obvious artifacts and a lower deflection for the less obvious one; this is in line with the previously reported results. In addition, classification on the EEG data was performed using support vector machine (SVM). …

Reading Faces. Using Hard Multi-Task Metric Learning for Kernel Regression
J Nicolle – 2016 – theses.fr
… ‘CompanionAble’1 led to Hector, a robot designed for assisting elderly people living alone. Among other abilities, it includes a personalized dialog system displaying emotional intelli- gence to avoid feelings of loneliness and offer cognitive stimulation through games. …

Designing Regularizers and Architectures for Recurrent Neural Networks
D Krueger – 2016 – papyrus.bib.umontreal.ca
… RNN Recurrent Neural Network SGD Stochastic Gradient Descent SL Supervised Learning SRNN Simple Recurrent Neural Network SVM Support Vector Machine TRec Threshold Rectified Linear Unit UL Unsupervised Learning x Page 11. ACKNOWLEDGMENTS …

Design and Development of the eBear: A Socially Assistive Robot for Elderly People with Depression
A Kargarbideh – 2016 – search.proquest.com
… 3.2.1 Interactivity. One difcult challenge in designing social robots is developing the spoken dialog system and natural language processing. … Then using a Support Vector Machine (SVM) classier, subjects are classied into those categories. …

Talk the walk: Empirical studies and data-driven methods for geographical natural language applications
J Götze – 2016 – diva-portal.org
… poi Point of Interest re referring expression rr reference resolution svm Support Vector Machine tts Text-to-Speech woz Wizard-of-Oz xv Page 17. Page 18. … In a spoken dialog system, the dialog manager is responsible for taking decisions that pertain to the flow of the dialog. …

A Study on the Effect of Design Factors of Slim Keyboard’s Tactile Feedback
KC Lin, CF Wu, HL Hsu, YH Tu, CC Wu – Topology, 2016 – waset.org
Conferences.

1st International Workshop on Multimodal Media Data Analytics (MMDA 2016)
S Vrochidis, M Melero, L Wanner, J Grivolla, Y Estève… – ecai2016.org
Page 1. ECAI 2016, MMDA 2016 workshop, August 2016 1st International Workshop on Multimodal Media Data Analytics (MMDA 2016) The rapid advancements of digital technologies, as well as the penetration of internet and …

Statistical task modeling of activities of daily living for rehabilitation
ÉMD Jean-Baptiste – 2016 – etheses.bham.ac.uk
… 12 1.1.3.4 Cue Generation Module . . . . . 14 1.1.4 Similarities with a Spoken Dialogue System . . . . . 14 1.2 Contribution . . . . . … 131 7.1.1.1 Support Vector Machine (SVM) . . . . 131 7.1.2 Metrics . . . . . …

Designing Human-Centered Collective Intelligence
ID Addo – 2016 – search.proquest.com
… That notwithstanding, non-verbal cues including gestures and facial expression can be identified using the camera inputs on the dialogue system. In. [28]. … Bayes Point Machine [90]- Support Vector Machine (SVM) [91]- Neural Networks [92]. …

The Essence of Smart Homes: Application of Intelligent Technologies
A Ghaffarianhoseini, A Ghaffarianhoseini… – Artificial Intelligence …, 2016 – books.google.com
… Similarly, Aslan et al.,(2015) presented an improved depth-based fall detection system. This system can use shape based fall characterization and a Support Vector Machine (SVM) classifier to classify falls from other daily actions. This system can accurately detect falls. 3.2. …

Language modeling for automatic speech recognition of inflective languages: an applications-oriented approach using lexical data
G Donaj, Z Ka?i? – 2016 – books.google.com
… The development of speech technologies enables a more natural way of interaction with computers systems. Several technologies are needed for such an interaction: speech recognition, dialog systems and speech synthesis. …

Language-independent methods for computer-assisted pronunciation training
A Lee – 2016 – dspace.mit.edu
… ReLU Rectified Linear Unit. RNN Recurrent Neural Network. SGD Stochastic Gradient Descent. SGMM Subspace Gaussian Mixture Model. SVM Support Vector Machine. TA True Acceptance. TR True Rejection. UBM Universal Background Model. 21 Page 22. 22 Page 23. …

Using linguistic knowledge for improving automatic speech recognition accuracy in air traffic control
VN Nguyen – 2016 – brage.bibsys.no
Page 1. Using Linguistic Knowledge for Improving Automatic Speech Recognition Accuracy in Air Traffic Control Master’s Thesis in Computer Science Van Nhan Nguyen May 18, 2016 Halden, Norway Page 2. Page 3. Abstract …

Automatic Annotation and Assessment of Syntactic Structures in Law Texts
K Sugisaki – 2016 – sugisaki.ch
… MaxEnt Maximal entropy MEMM Maximum entropy Markov model ML Machine learning NLP Natural language processing SVM Support vector machine XML Extensible markup language General linguistic terms COMP Complementizer CONJ Subordinating conjunction …

A Corpus Driven Computational Intelligence Framework for Deception Detection in Financial Text
SZ Minhas – 2016 – dspace.stir.ac.uk
… 222 6.8.4 Support Vector Machine (SVM) …. 226 … SGB: Stochastic Gradient Boosting SFL: Systemic-Functional Linguistics () SVM: Support Vector Machine TDM: Term Document Matrix tm: text miner VSM: Vector Space Models …

Automatic recognition of the speaker’s dialect
W Peerlinck – 2016 – lib.ugent.be
… PPRLM Parallel Phone Recognition followed by Language Modeling PRML Phone Recognition followed by Language Modeling SDC Shifted Delta Cepstral SVM Support Vector Machine SER Speaker Error Rate TV Total Variability UBM Universal Background Model …

Automatic Recognition of Code-Switched Speech in Sepedi
TI Modipa – 2016 – dspace.nwu.ac.za
… SAMPA Speech Assessment Methods Phonetic Alphabet SDS Spoken Dialogue System SPCS Sepedi Prompted Code-Switched … Chapter 1 Introduction Spoken dialogue systems (SDSs) are automated systems that use voice as input and output when interacting with a user. …

Syntactic and referential choice in corpus-based generation: modeling source, context and interactions
S Zarrieß – 2016 – elib.uni-stuttgart.de
Page 1. Syntactic and Referential Choice in Corpus-based Generation: Modeling Source, Context and Interactions Von der Fakultät für Informatik, Elektrotechnik und Informationstechnik der Universität Stuttgart zur Erlangung …

Automatic sarcasm detection: A survey
A Joshi, P Bhattacharyya, MJ Carman – arXiv preprint arXiv:1602.03426, 2016 – arxiv.org
Page 1. A Automatic Sarcasm Detection: A Survey ADITYA JOSHI, IITB-Monash Research Academy PUSHPAK BHATTACHARYYA, Indian Institute of Technology Bombay MARK J CARMAN, Monash University Automatic sarcasm …

An Investigation into Language Model Data Augmentation for Low-Resourced STT and KWS}}
G Huang, TF da Silva, L Lamel, JL Gauvain, A Gorin… – ieeeicassp, 2016 – perso.limsi.fr
… roles. Lexical approaches achieve low error rates for certain speaker roles such as anchors and journalists, sometimes lower than a standard cepstral-based Gaussian Supervector – Support Vector Machine (GSV-SVM) system. …

Large-scale affective computing for visual multimedia
B Jou – 2016 – search.proquest.com
… vii, 79, 96, 97, 99, 104, 106, 110115, 117. SGD stochastic gradient descent. 80, 84, 110. SNE Stochastic Neighbor Embedding. 65SVM Support Vector Machine. 2022, 37, 38, 90, 93, 94, 125, 127, 138. VA valence-arousal. 12, 13, 20, 43, 90, 131, 132, 142. …

Automatic text and speech processing for the detection of dementia
K Fraser – 2016 – search.proquest.com
Automatic text and speech processing for the detection of dementia. Abstract. Dementia is a gradual cognitive decline that typically occurs as a consequence of neurodegenerative disease, and can result in language deficits (ie, aphasia). …