Decision Tree Classifier & Dialog Systems


See also: 

100 Best Decision Tree Videos | Classifier & Dialog Systems 2011Classifiers In Dialog SystemsDecision Tree & Dialog Systems 2011 | Dialog Systems


[CITATION] Semi-automated classifier adaptation for natural language call routing SM Witt – Twelfth Annual Conference of the International Speech …, 2011 Related articles All 2 versions

[PDF] from docsdrive.com [PDF] K-Meaiis Clustering to Improve the Accuracy of Decision Tree Response Classification SA Ali, N Sulaiman, A Mustapha… – Information technology …, 2009 – docsdrive.com … utterance plays in the dialogue act (eg, a question for information or a request to perform an action), dialogue systems need to … The result shows that the Decision tree classifier is well suited for classification task, where the classifier performances achieved the best accuracy as … Cited by 7 Related articles All 8 versions

[PDF] from aclweb.org [PDF] Incremental speech understanding in a multi-party virtual human dialogue system D DeVault, D Traum – NAACL-HLT 2012, 2012 – aclweb.org … Extended Abstract This demonstration highlights some emerging ca- pabilities for incremental speech understanding and processing in virtual human dialogue systems. … et al., 2009) and (DeVault et al., 2011a), we explored the use of data-driven decision tree classifiers to make … Cited by 1 Related articles All 9 versions

[PDF] from usc.edu Combining lexical, syntactic and prosodic cues for improved online dialog act tagging VK Rangarajan Sridhar, S Bangalore… – Computer Speech & …, 2009 – Elsevier … The likelihoods due to multiple knowledge sources were decoupled and a prosodic decision tree classifier was used to estimate the likelihood (obtained from the posterior probability through Bayes rule) of the dialog acts during training. … Cited by 20 Related articles All 6 versions

[PDF] from psu.edu [PDF] Evaluating language understanding accuracy with respect to objective outcomes in a dialogue system MO Dzikovska, P Bell, A Isard, JD Moore – … of the 13th Conference of the …, 2012 – Citeseer … using the Akaike information criterion (AIC) for variable 2We also experimented with using% unclassified as an additional feature, since% of rejections is known to be a problem for spoken dialogue systems. … We built a decision tree classifier using the Weka implementation of C4 … Related articles All 11 versions

[PDF] from aclweb.org [PDF] Towards effective tutorial feedback for explanation questions: A dataset and baselines MO Dzikovska, RD Nielsen, C Brew – … of the 2012 Conference of the …, 2012 – aclweb.org … The BEETLE corpus consists of the interactions be- tween students and the BEETLE II tutorial dialogue system (Dzikovska et al., 2010b … To provide a higher baseline that is compara- ble across both subsets of the data, we built a simple decision tree classifier using the Weka 3.6 … Cited by 1 Related articles All 6 versions

[PDF] from cai.sk A Comparison of Decision Tree Classifiers for Automatic Diagnosis of Speech Recognition Errors M Cernak – Computing and Informatics, 2012 – cai.sk … 2 DECISION TREE CLASSIFIERS … 3, pp. 241–246. [17] Juhár, J.—Rusko, M. et al.: Development of Slovak GALAXY/VoiceXML Based Spoken Language Dialogue System to Retrieve Information from the Internet. Inter- speech – ICSLP, Pittsburgh, USA, 2006, pp. 485–488. … Cited by 1 Related articles All 4 versions

[PDF] from docsdrive.com [PDF] Improving accuracy of intention-based response classification using decision tree SA AH, N Sulaiman, A Mustapha… – Information Technology …, 2009 – docsdrive.com … Decision tree classifier is tested on 64 mixed-initiative, transaction dialogue corpus in theater domain. … Key words: Classification, decision tree, natural language generation, dialogue systems INTRODUCTION A dialog system is a computer system intended to converse with a … Cited by 1 Related articles All 7 versions

An enhanced approach for classifying emotions using customized decision tree algorithm S Sriram, X Yuan – Southeastcon, 2012 Proceedings of IEEE, 2012 – ieeexplore.ieee.org … The implementation of the customized decision tree classifier has to calculate the global mean and RMS values of seven features. … This motivated us to create a system that combines the current state-of-the-art 3D facial animation with a spoken dialogue systems, along with a … Related articles

Using a slim function word classifier to recognise instruction dialogue acts J O’Shea, Z Bandar, K Crockett – Agent and Multi-Agent Systems: …, 2011 – Springer … Nevertheless, the results of the decision tree classifiers produced provide evidence for potentially highly effective classification and they are comparable with … This assumption is supported by prior work in dialogue systems [6] and robotics [7]. Examples of these DAs are: “Is the … Cited by 1 Related articles All 3 versions

[PDF] from elanguage.net [PDF] Concept type prediction and responsive adaptation in a dialogue system S Stoyanchev, A Stent – Dialogue & Discourse, 2012 – elanguage.net … Concept Type Prediction and Responsive Adaptation in a Dialogue System Svetlana Stoyanchev … Editor: Gregory Aist Abstract Responsive adaptation in spoken dialogue systems involves a change in dialogue system behavior in response to a user or a dialogue situation. … Cited by 1 Related articles All 2 versions

Recognizing child’s emotional state in problem-solving child-machine interactions S Yildirim, S Narayanan – Proceedings of the 2nd Workshop on Child, …, 2009 – dl.acm.org … One of the steps toward building natural and responsive spo- ken interfaces is to enable automatic emotion recognition ca- pability within a spoken dialog system framework. … As can be observed from the table, SVC performed better than k-NN, LDC and decision tree classifiers. … Related articles

A multi-classifier approach to dialogue act classification using function words J O’Shea, Z Bandar, K Crockett – Transactions on Computational …, 2012 – Springer … DM techniques support the production of Dialogue Systems (DSs) which will allow ordinary users to interact with increasingly powerful and complex … training cases were used to construct each classifier (a rule of thumb recommended by Quinlan for Decision Tree classifiers [25 … Related articles All 2 versions

[PDF] from cmu.edu Incorporating a user model to improve detection of unhelpful robot answers M Makatchev, R Simmons – … , 2009. RO-MAN 2009. The 18th …, 2009 – ieeexplore.ieee.org … Adapting to the model of a user’s knowledge and/or emotional state (in short, a user model) has been shown to improve performance of dialogue systems on such … We used this manually labeled corpus of dialogues to train decision tree classifiers for each of the dialogue acts. … Related articles All 6 versions

PADUA: a protocol for argumentation dialogue using association rules M Wardeh, T Bench-Capon, F Coenen – Artificial Intelligence and Law, 2009 – Springer … knowledge based systems throughout their history. If we see the dialogue system as a way of adding value to existing systems, we will find that there are very few suitable belief bases available. In contrast, there are many large … Cited by 9 Related articles All 4 versions

[PDF] from att.com Location grounding in multimodal local search P Ehlen, M Johnston – … Conference on Multimodal Interfaces and the …, 2010 – dl.acm.org … view. Given the combination of numeric and categorical features, we chose a decision tree classifier, specifically the J48 implementation in the WEKA toolkit [19]. For the evaluation, we conducted a 10-fold cross validation. In … Cited by 7 Related articles All 3 versions

[PDF] from universityoftexasatdallascomets.com [PDF] Classifying clear and conversational speech based on acoustic features A Amano-Kusumoto, JP Hosom… – Proceedings …, 2009 – universityoftexasatdallascomets.com … Index Terms: binary classification, acoustic features, decision tree classifier, multilayer perceptron, 1. Introduction … The accurate classification of speaking style can not only help improve speech recognition but also help tailor strategies in a spoken dialog system. … Cited by 3 Related articles All 17 versions

[PDF] from psu.edu [PDF] Topic segmentation M Purver – … : Systems for Extracting Semantic Information from …, 2011 – Citeseer … Clearly, this is only a useful task when applied to recordings of some length – short segments of speech such as an utterance in a typical spoken dialogue system tend already to be topically homogeneous and thus not to require segmentation. … Cited by 10 Related articles All 5 versions

[PDF] from andrewkun.com An investigation of interruptions and resumptions in multi-tasking dialogues F Yang, PA Heeman, AL Kun – Computational Linguistics, 2011 – MIT Press … These research works show the usefulness of a spoken dialogue system being able to handle multiple tasks, and promote a thorough examination of multi-tasking dialogue. In this article we examine the conventions of task … Cited by 4 Related articles All 17 versions

[PDF] from syntheticspeech.de [PDF] Voice attributes affecting likability perception B Weiss, F Burkhardt – Proc. Interspeech, 2010 – felix.syntheticspeech.de … As a classification engine, the LADT (LogitBoost Alter- nating Decision Trees) classifier implemented by the WEKA toolkit [20] was used … 6. References [1] F. Burkhardt, R. Huber, and A. Batliner, “Application of speaker classification in human machine dialog systems,” in Speaker … Cited by 7 Related articles All 3 versions

[PDF] from harvard.edu Identifying uncertain words within an utterance via prosodic features HR Pon-Barry, SM Shieber – … of the 10th Annual Conference of …, 2009 – dash.harvard.edu … For ex- ample, this would occur in a tutorial dialogue system when the speaker answers a direct question (Pon- Barry et al., 2006; Forbes-Riley et al., 2008), or in language (foreign or ESL) learning systems and lit- eracy systems (Alwan et al., 2007) when new vocab- ulary is … Cited by 4 Related articles All 11 versions

PISA: A framework for multiagent classification using argumentation M Wardeh, F Coenen, TB Capon – Data & Knowledge Engineering, 2012 – Elsevier This paper describes an approach to multi-agent classification using an argumentation from experience paradigm whereby individual agents argue for a given examp. Related articles All 2 versions

[PDF] from psu.edu [PDF] Predicting concept types in user corrections in dialog S Stoyanchev, A Stent – Proceedings of the EACL Workshop on the …, 2009 – Citeseer … sys- tem, a telephone-based spoken dialog system that provides information about bus routes in Pitts- burgh (Raux et al., 2005). … We used Weka’s implementation of the J48 decision tree classifier (Witten and Frank, 2005) 2. For each experiment, we report precision (pre+) and … Cited by 9 Related articles All 14 versions

[PDF] from upenn.edu [PDF] Dialogue with attitude: The contribution of cue words and prosodic meaning in conversational speech C Lai – 2011 – ling.upenn.edu … To further test this hypothesis, two classifiers were built in an attempt to separate the data. ? Decision Tree classifier (DTree) (j48 in RWeka). ? A Support Vector Machine (SVM) classifier with radial basis function kernel (libsvm via R), parameter determined by grid search. … Related articles

[PDF] from utwente.nl Towards affective state modeling in narrative and conversational settings B Jochems, M Larson, R Ordelman, R Poppe… – 2010 – doc.utwente.nl … This sort of diversity offers a possible explanation for the strength of the J48 decision tree classifier, which imposes no assumptions concerning … The corpus was created by the SEMAINE project, which aims to build SALs, multimodal dialogue systems with the social interaction … Cited by 1 Related articles All 8 versions

[PDF] from aclweb.org Evaluating automatic extraction of rules for sentence plan construction A Stent, M Molina – Proceedings of the SIGDIAL 2009 Conference: The …, 2009 – dl.acm.org … 6.3 Discriminative Power In this evaluation, we train decision tree classifiers for each sentence plan construction task. … O. Rambow, S. Bangalore, and MA Walker. 2001. Natural language generation in dialog systems. In Proceedings of HLT. E. Reiter and R. Dale. 2000. … Cited by 3 Related articles All 13 versions

[PDF] from harvard.edu The Importance of Sub-Utterance Prosody in Predicting Level of Certainty SM Shieber, HR Pon-Barry – … : The 2009 Annual Conference of the …, 2009 – dash.harvard.edu … For ex- ample, this would occur in a tutorial dialogue system when the speaker answers a direct question (Pon- Barry et al., 2006; Forbes-Riley et al., 2008), or in language (foreign or ESL) learning systems and lit- eracy systems (Alwan et al., 2007) when new vocab- ulary is … Related articles All 3 versions

[PDF] from kfupm.edu.sa [PDF] A Preliminary Study of Prosody Based Detection of Questions in Arabic Speech Monologues O Khan, WG Al-Khatib, L Cheded – Arabian Journal for Science …, 2010 – ajse.kfupm.edu.sa … Their decision tree classifier, C4.5, achieved an error rate of 14.9% with respect to a 50% chance-level rate. Quang et al. … [28]. This research was carried out on a corpus of spoken tutor dialogues for the development of intelligent tutoring spoken dialogue systems. … Related articles

[PDF] from diva-portal.org Message classification as a basis for studying command and control communications—an evaluation of machine learning approaches O Leifler, H Eriksson – Journal of Intelligent Information Systems, 2012 – Springer Page 1. J Intell Inf Syst DOI 10.1007/s10844-011-0156-5 Message classification as a basis for studying command and control communications—an evaluation of machine learning approaches Ola Leifler·Henrik Eriksson Received … Cited by 3 Related articles All 5 versions

Automated communication analysis of teams PW Foltz, MJ Martin – Team Effectiveness in Complex …, 2008 – books.google.com … learning techniques have been applied to discourse modeling, generally for the purpose of improving speech recognition and dialogue systems. … A decision-tree classifier is constructed by recursively partitioning the training data (an already classified set of utterances) based on … Cited by 10 Related articles

Mining preorder relation between knowledge units from text J Liu, L Jiang, Z Wu, Q Zheng, Y Qian – … of the 2010 ACM Symposium on …, 2010 – dl.acm.org … For example, Fleischman and Hovy described a method for recognizing hyponymy relations by a decision tree classifier in which each relation pair is represented in terms of their template and adjacent features [7 … An Interactive Dialogue System for Knowledge Acquisition in CYC … Cited by 2 Related articles All 3 versions

[PDF] from ogi.edu Switching to real-time tasks in multi-tasking dialogue F Yang, PA Heeman, A Kun – … of the 22nd International Conference on …, 2008 – dl.acm.org … They built a multi-tasking dialogue system for a human operator to direct a robotic helicopter on executing multiple tasks, such as searching for a car and flying to a tower. … We train a decision tree classifier (C4.5) to discriminate task switching from poker playing. … Cited by 7 Related articles All 20 versions

Improving Automatic Classification of Prosodic Events by Pairwise Coupling C González-Ferreras… – Audio, Speech, and …, 2012 – ieeexplore.ieee.org … lems provide high accuracy results. Furthermore, complementarity between Artificial Neural Networks and Decision Trees classifiers has been exploited to improve the final system, combining their outputs using a fusion method. … Related articles

[CITATION] Topic Switching Strategies for Spoken Dialogue Systems T Heinroth, S Koleva, W Minker – Twelfth Annual Conference of the International …, 2011 Related articles All 2 versions

[PDF] from columbia.edu [PDF] Error Handling in Spoken Dialogue Systems S Stoyanchev – 2012 – web1.cs.columbia.edu Page 1. 1 Error Handling in Spoken Dialogue Systems Svetlana Stoyanchev CS 4706: Spoken Language Processing April 16, 2012 Page 2. 2 Outline … dialogue ? How do dialogue systems handle errors ? Overview of dialogue system strategies ? Evaluation of mobile devices … Related articles All 5 versions

[PDF] from sas.ac.uk Classifying non-sentential utterances in dialogue: A machine learning approach R Fernández, J Ginzburg, S Lappin – Computational Linguistics, 2007 – dl.acm.org … Our aim in doing so is to develop a classification model whose output can be fed into a dialogue processing system—be it a full dialogue system or, for instance, an automatic dialogue summarization system—to boost its NSU resolution capability. … Cited by 21 Related articles BL Direct All 25 versions

[PDF] from liv.ac.uk Argument based moderation of benefit assessment M Wardeh, TJM Bench-Capon… – Proceedings of the 2008 …, 2008 – books.google.com … In this paper we describe how we can exploit an argumentation based dialogue system, PADUA (Protocol for Argumentation Dialogue … While, however, the decision tree classifiers perform rather consistently throughout the ten trials, there is more variation in PADUA, especially … Cited by 3 Related articles All 9 versions

[PDF] from sri.com Speech segmentation and spoken document processing M Ostendorf, B Favre, R Grishman… – Signal Processing …, 2008 – ieeexplore.ieee.org … model) characterizing the event labels and words jointly. The observation posteriors P(F|E) are generated from a prosody model (eg, a decision tree classifier or neural network). HMMs that are discriminatively trained have also … Cited by 23 Related articles BL Direct All 26 versions

[PDF] from cmaltese.com Call classification for automated troubleshooting on large corpora K Evanini, D Suendermann… – … Speech Recognition & …, 2007 – ieeexplore.ieee.org … They were manually transcribed and classified into one of several distinct call rea- sons that are acted upon by the dialog system, such as Chan- nelMissing for TV or CantLoginPasswordEmail for INT (for the corpus statistics, refer to Section 2 … C4.5 is a decision tree classifier [19 … Cited by 12 Related articles All 17 versions

[PDF] from univ-avignon.fr On the use of finite state transducers for semantic interpretation C Raymond, F Bechet, R De Mori, G Damnati – Speech Communication, 2006 – Elsevier … The dialogue corpus used for training and evaluating these algorithms is made of dialogue traces of the France Telecom R&D spoken dialogue system PlanResto (Sadek et al., 1996) which is a booking restaurant application. … Cited by 45 Related articles All 7 versions

[PDF] from washington.edu [PDF] Non-segmental duration feature extraction for prosodic classification A Dashiell, B Hutchinson, A Margolis… – Proc. of …, 2008 – ssli.ee.washington.edu … For speech transcription aimed at spoken document processing and dialog systems, it can be useful to recognize segmentation and emphasis patterns along with the words. … The results are combined using a decision tree classifier to improve over the individual methods. … Cited by 1 Related articles All 3 versions

[HTML] from nih.gov Fine-grained pitch accent and boundary tone labeling with parametric f0 features S Ananthakrishnan, S Narayanan – Acoustics, Speech and …, 2008 – ieeexplore.ieee.org … For instance, text-to-speech (TTS) systems can use these la- bels to generate human-like prosody, while dialog systems may find them … 3-way pitch accent iden- tification (H*, !H* and L*) and 3-way boundary classifica- tion (LL%, HL% and LH%) using a decision tree classifier. … Cited by 11 Related articles All 8 versions

[PDF] from iaied.org Predicting affective states expressed through an emote-aloud procedure from AutoTutor’s mixed-initiative dialogue SK D’Mello, SD Craig, J Sullins… – International Journal of …, 2006 – IOS Press Page 1. International Journal of Artificial Intelligence in Education 16 (2006) 3–28 3 IOS Press 1560-4292/06/$17.00 © 2006 – IOS Press and the authors. All rights reserved Predicting Affective States expressed through an Emote-Aloud Procedure from AutoTutor’s Mixed- … Cited by 70 Related articles All 12 versions

Soft computing in intelligent tutoring systems and educational assessment R Nielsen, W Ward, J Martin – Soft Computing Applications in Business, 2008 – Springer Page 1. B. Prasad (Ed.): Soft Computing Applications in Business, STUDFUZZ 230, pp. 201–230, 2008. springerlink.com © Springer-Verlag Berlin Heidelberg 2008 Soft Computing in Intelligent Tutoring Systems and Educational Assessment … Cited by 2 Related articles All 2 versions

[PDF] from upenn.edu Noun phrase generation for situated dialogs L Stoia, DM Shockley, DK Byron… – Proceedings of the fourth …, 2006 – dl.acm.org … Then, using this data, we trained a decision-tree classifier to utilize con- text variables such as distance, target object visi- bility, discourse history, etc., to determine lexical properties of referring expressions to be produced by the generation component of our dialog system. … Cited by 23 Related articles All 28 versions

[PDF] from rug.nl Modeling user satisfaction transitions in dialogues from overall ratings R Higashinaka, Y Minami, K Dohsaka… – Proceedings of the 11th …, 2010 – dl.acm.org … of dialogue systems without the costly process of performing surveys with human sub- jects, leading to a rapid improvement cycle for dialogue systems. … and dialogue man- agement features from the first few turns of a dia- logue and apply a decision tree classifier to detect … Cited by 3 Related articles All 10 versions

[PDF] from utwente.nl Predicting dialogue state transitions using prosodic markers: Exploring AMI Corpus backchannels ICC Nouwens – 2009 – essay.utwente.nl … the late 90’s and early in the 21st century that extra modalities, like non-verbal communication with hand gestures, or gazing behavior were taken into account in (spoken) dialogue systems. … 9 wherein the functional merit of the feature was determined by decision tree classifiers. … Cited by 1 Related articles All 3 versions

[PDF] from psu.edu [PDF] Yeah right: Sarcasm recognition for spoken dialogue systems J Tepperman, D Traum, S Narayanan – InterSpeech ICSLP, 2006 – Citeseer … dependent on the assumed intentions and mutual beliefs held by all dialogue participants [1]. In the realm of spoken dialogue systems, the use … This decision tree classifier, trained on the C4.5 algorithm implemented in the Weka toolkit [9], was chosen because of its versatility in … Cited by 12 Related articles All 10 versions

Dialogue act recognition under uncertainty using bayesian networks S Keizer, RO Akker – Natural Language Engineering, 2007 – Cambridge Univ Press … We think that Bayesian networks form a promising technique for use in dialogue systems, and our experiments on dialogue act classification confirm that hypothesis, although much further research lies ahead. In Keizer (2003 … Cited by 9 Related articles BL Direct All 13 versions

[PDF] from aclweb.org Prepositions in applications: A survey and introduction to the special issue T Baldwin, V Kordoni, A Villavicencio – Computational Linguistics, 2009 – MIT Press … human interaction with those objects. Along these lines, Kelleher and Costello (2009) propose computational models of spatial preposition semantics for use in visually situated dialogue systems. Finally, with locative prepositions … Cited by 13 Related articles All 19 versions

[PDF] from ia.ac.cn Predicting and Tagging Dialog-Act Using MDP and SVM K Zhou, C Zong, H Wu, H Wang – Chinese Spoken Language …, 2008 – ieeexplore.ieee.org … Dialog-act is widely used in speech recognition [3] and spoken dialog system [13]. … For the dialog-act tagging, the previous work is usually based on the maximum entropy methods and decision tree classifiers [9] [1]. In the recently years, new techniques on classifier have been … Related articles All 14 versions

[PDF] from umi.com Trainable English generation with modifier and adjunct ordering H Zhong – 2010 – gradworks.umi.com … In Proceedings of the Workshop on Empirical and Statistical Approaches for Spoken Dialogue Systems at AAAI, 2006. • H. Guo and H. Zhong. … NLG has many appealing applications, including dialog systems, automatic question answering, automatic summarization … Related articles All 2 versions

[PDF] from aminer.org Comparison and combination of confidence measures G Stemmer, S Steidl, E Nöth, H Niemann… – Text, Speech and …, 2006 – Springer … A spoken dialogue system may simply ignore all inserted words, but ask back if there has been a substitution. … For each of the individual features we train a decision tree classifier which has to assign the label correct or wrong to each word which has been hypothesized by the … Cited by 12 Related articles BL Direct All 14 versions

Embedded Modules for Speaker Classification M Feld – … Computing, 2008 IEEE International Conference on, 2008 – ieeexplore.ieee.org … Fig. 5 illustrates the difference between these three methods at the example of a decision tree classifier. Sometimes … file. classification is embedded in a server application, for exam- ple a dialog system running in a large call center. … Cited by 1 Related articles All 3 versions

Handheld speech to speech translation system Y Gao, B Zhou, W Zhu, W Zhang – Automatic Speech Recognition on …, 2008 – Springer … The context-dependent states are generated using a decision-tree classifier. … 2004) and CLIPS (Blanchon and Boitet 2000), etc. The NLU module is based on the statistical parser employed in IBM telephony natural language dialog systems. … Cited by 2 Related articles All 2 versions

[PDF] from mit.edu Methods for pronunciation assessment in computer aided language learning MA Peabody – 2011 – dspace.mit.edu … We make several assumptions about the nature of the learning activity: it takes place using a dialogue system, it is a task- or game-oriented activity, the student should not be interrupted by the pronunciation feedback system, and that the goal of … 5.3.4 Decision Tree Classifier . . . … Cited by 2 Related articles All 4 versions

[PDF] from academypublisher.com [PDF] Lexical Structure for Dialogue Act Recognition P Král, C Cerisara, J Klecková – Journal of Multimedia, 2007 – academypublisher.com … In [9], the duration, pause, fundamental frequency (F0), energy and speaking rate prosodic attributes are modeled by a CART-style decision trees classifier. In [16], prosody is used to segment utterance. The duration, pause, F0- contour and energy features are used in [17], [18]. … Cited by 5 Related articles All 14 versions

Evaluation of dialogue act recognition approaches P Kral, T Pavelka, C Cerisara – Machine Learning for Signal …, 2008 – ieeexplore.ieee.org … The DA recognition module shall be used to improve the performance ofan automatic dialogue system by allow- ing it to better … the duration, pause, fundamental fre- quency (FO), energy and speaking rate prosodic features are modeled by a CART-style decision trees classifier. … Related articles All 4 versions

Automated grammatical error detection for language learners C Leacock, M Chodorow, M Gamon… – Synthesis lectures on …, 2010 – 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 … Cited by 34 Related articles All 10 versions

[PDF] from upenn.edu Sentence planning for realtime navigational instructions L Stoia, DK Byron, DM Shockley… – Proceedings of the …, 2006 – dl.acm.org … The con- tent planner of a spoken dialog system must decide which of these dialog moves to produce at each turn. … The Weka1 toolkit was used to build a decision tree classifier (Witten and Frank, 2005). Figure 4 shows the resulting tree. … Cited by 10 Related articles All 23 versions

[PDF] from illinois.edu Cognitive state classification in a spoken tutorial dialogue system T Zhang, M Hasegawa-Johnson, SE Levinson – Speech communication, 2006 – Elsevier … 6. Conclusion; Acknowledgments; References. 1. Introduction. 1.1. A multimodal spoken tutorial dialogue system. An intelligent tutoring system (ITS) is a computer program that seeks to tutor users in an educational subject. … 1.2. User affect in the tutorial dialogue system. … Cited by 7 Related articles All 14 versions

[PDF] from pitt.edu [PDF] Combination of classifiers for automatic recognition of dialog acts P Kral, C Cerisara, J Kleckova – Interspeech’2005, 2005 – cs.pitt.edu … The dialog system shall exploit dialog … In [2], the duration, pause, fundamental fre- quency (F0), energy and speaking rate prosodic attributes are modeled by a CART-style decision trees classifier. In [10], prosody is used to segment utterance. … Cited by 12 Related articles All 8 versions

[PDF] from umi.com [BOOK] Impact of responsive and directive adaptation on local dialog processing S Stoyanchev – 2010 – gradworks.umi.com … 2009 Spoken dialog systems allow users to access information and accomplish tasks using speech. … one conversational partner’s behavior causing changes in the behavior of the other conversational partner) can be a powerful tool to improve dialog system performance. … Cited by 1 Related articles All 6 versions

[PDF] from aclweb.org Modeling Regular Polysemy: A Study on the Semantic Classification of Catalan Adjectives G Boleda, S Schulte im Walde, T Badia – Computational Linguistics, 2012 – MIT Press … this article. The semantic properties of adjectives can also be exploited in advanced NLP tasks and applications such as Question Answering, Dialog Systems, Natural Language Generation, or Information Extraction. For instance … Cited by 1 Related articles All 8 versions

[PDF] from aclweb.org [PDF] Feature weighting random forest for detection of hidden web search interfaces Y Ye, H Li, X Deng, JZ Huang – Computational Linguistics and Chinese …, 2009 – aclweb.org … for each decision tree. The new algorithm can automatically remove the noisy features in search forms so that decision tree classifiers can be learned from more representative subsets of the feature space. 3. We conducted experiments … Cited by 4 Related articles All 15 versions

[PDF] from eurasip.org [PDF] Analysis of disfluent repetitions in spontaneous speech recognition V Rangarajan, S Narayanan – Proc. EUSIPCO 2006, 2006 – eurasip.org … growing demand for reliable spontaneous speech recognizers has been manifested in applications such as dialogue systems, spoken document … Decision tree classifiers are used with discrete features like duration, distance from pause and normalized f0 values [6]. Assuming … Cited by 8 Related articles All 4 versions

[PDF] from uvt.nl [PDF] Timbl: Tilburg memory-based learner W Daelemans, J Zavrel, K Van der Sloot… – Version, 2007 – ilk.uvt.nl … While the decision tree can be used to retrieve the exact k-nearest neighbors (as happens in the IB1 algorithm within TiMBL), it can also be deterministically traversed as in a decision-tree classifier (the method adopted by the IGTREE algorithm). … Cited by 96 Related articles All 6 versions

[PDF] from rodneynielsen.com [BOOK] Learner answer assessment in intelligent tutoring systems RD Nielsen – 2007 – books.google.com Page 1. LEARNER ANSWER ASSESSMENT IN INTELLIGENT TUTORING SYSTEMS by RODNEY D. NIELSEN MS, University of Colorado, Boulder, 2005 A thesis submitted to the Faculty of the Graduate School of the University … Cited by 1 Related articles All 7 versions

[PDF] from utwente.nl Detecting emotional intensity peaks in narrative conversational settings B Jochems – 2010 – essay.utwente.nl Page 1. Human Media Interaction University of Twente PO Box 217, 7500 AE Enschede The Netherlands Detecting Emotional Intensity Peaks in Narrative and Conversational Settings by Bart Jochems behjochems@student.utwente.nl July 2, 2010 Committee … Related articles All 2 versions

[BOOK] Procedural Or Non-procedural: That is the Question KK Wu – 2007 – books.google.com … UNIX editing program, emacs, dating back to the 1970’s, or more famously, the psychotic HAL 9000 computer system in Stanley Kubrick’s 2001: A Space Odyssey; question answering researchers are likely to contend, quite legitimately, that these are dialogue systems and an … All 3 versions

[PDF] from ncsu.edu [BOOK] Early prediction of student goals and affect in narrative-centered learning environments S Lee – 2008 – books.google.com Page 1. ABSTRACT LEE, SUNYOUNG. Early Prediction of Student Goals and Affect in Narrative-Centered Learning Environments. (Under the direction of James C. Lester and Carla D. Savage.) Recent years have seen a growing … Related articles All 7 versions

[PDF] from gate.ac.uk [PDF] Enabling browsing in interactive systems JH Polifroni – 2007 – gate.ac.uk … 32 2.6 Generating summary responses in dialogue systems . . . . . 34 2.7 Conclusion . . . . . … 4.2 Applying machine learning to corpus . . . . . 48 4.3 Advantages of using decision tree induction for dialogue systems 50 4.4 Database used . . . . . … Cited by 2 Related articles All 3 versions

[PDF] from dhbw-stuttgart.de [PDF] Emotion and Computing–Current Research and Future Impact D Reichardt, P Levi, JJC Meyer – 2009 – wwwlehre.dhbw-stuttgart.de … Several approaches have been made concerning emotion recognition, emotion modelling, generation of emotional user interfaces and dialogue systems as well as anthropomorphic communication agents. Motivations for emotional computing are manifold. … Cited by 1 Related articles All 13 versions

[PDF] from wseas.us [PDF] A new automated information retrieval system by using intelligent mobile agent HM El-Bakry, AM Riad, A Atwan, SA El-Ghany… – Proceedings of the 9th …, 2010 – wseas.us … By 1970 several different techniques had been shown to perform well on small text corpora such as the Cranford collection (several thousand documents) [27]. Large-scale retrieval systems, such as the Lockheed Dialog system, came into use early in the 1970s. … Related articles All 2 versions

The Dynamic Lexicon S Goronzy, S Rapp, M Emele – … of Multimodal Dialogue Systems, 2006 – Springer … 2.2 “Updateable” Content It is to be expected that not all words that are used in a dialogue system change frequently. … We examine the influence of training parameters on size and accuracy of decision tree classifiers to optimise space in the first stage. … Cited by 1 Related articles All 2 versions

[PDF] from sharif.edu User Modeling Using Network Layer Information K Mizanian, M Analoui, R Zakeri… – … Conference on Systems …, 2006 – ieeexplore.ieee.org … In this case study we have used a decision tree classifier as the user classification engine. … [17] DN Chin, “KNOME: Modeling What the User Knows in UC”, User Models in Dialog Systems, Springer, Berlin, Heidelberg, 1989, pp. 74-107. … Cited by 1 Related articles All 6 versions

[PDF] from psu.edu [PDF] A hybrid model for spontaneous speech understanding T Zhang, M Hasegawa-Johnson, S Levinson – Proceedings of the AAAI …, 2005 – Citeseer … Adult users of a typical dialogue system (eg, for purchase of air travel or financial instruments) are usually able to … Tutoring Event Classification We applied See5 (Rulequest Research, 2004), a decision tree classifier, to combine the two distinct information sources, semantic … Cited by 6 Related articles All 12 versions

[PDF] from memetic-vre.net [PDF] Investigations into the distribution of backchannels in argumentative multi-party discourse and their functional determinants D Heylen, R op den Akker – Manuscript, HMI Research group, …, 2006 – memetic-vre.net Page 1. Investigations into the distribution of back-channels in argumentative multi-party discourse and their functional determinants Dirk Heylen and Rieks op den Akker Human Media Interaction, University of Twente, Enschede, the Netherlands. September 2, 2006 … Cited by 1 Related articles

[PDF] from cmu.edu [PDF] Improving the Performance of LVCSR Using Ensemble of Acoustic Models R Zhang – 2006 – cs.cmu.edu Page 1. Improving the Performance of LVCSR Using Ensemble of Acoustic Models Thesis Proposal By Rong Zhang Language Technologies Institute School of Computer Science Carnegie Mellon University May, 2006 Committee: Alexander Rudnicky Tanja Schultz … Related articles

A multiple classifier approach to detect Chinese character recognition errors KY Hung, RWP Luk, DS Yeung, KFL Chung, W Shu – Pattern recognition, 2005 – Elsevier Detection of recognition errors is important in many areas, such as improving recognition performance, saving manual effort for proof-reading and post-editing,. Cited by 4 Related articles All 3 versions

[PDF] from usf.edu Combining Natural Language Processing and Statistical Text Mining: A Study of Specialized Versus Common Languages J Jarman – 2011 – scholarcommons.usf.edu Page 1. University of South Florida (USF) Scholar Commons Graduate School Theses and Dissertations USF Graduate School 1-1-2011 Combining Natural Language Processing and Statistical Text Mining: A Study of Specialized Versus Common Languages … All 2 versions

[PDF] from neu.edu Natural noun phrase variation for interactive characters DK Byron, A Dalwani, R Gerritsen, M Keck… – Proceedings of the First …, 2005 – aaai.org … A decision tree classifier was built that predicts the form of 51% of the referring expressions, compared to a baseline of 39% achieved by a … For example, in the TRIPS spoken dialog system (Ferguson & Allen 1998), the Reference Manager deter- mines the meaning of referring … Cited by 2 Related articles All 9 versions

Application design for wearable computing D Siewiorek, A Smailagic… – Synthesis Lectures on …, 2008 – morganclaypool.com Page 1. Application Design for Wearable Computing Page 2. Page 3. iii Editor Mahadev Satyanarayanan, Carnegie Mellon University Mobile computing and pervasive computing represent major evolutionary steps in distributed … Cited by 11 Related articles All 3 versions

[PDF] from uni-osnabrueck.de [PDF] Learning the semantics of Wikipedia hyperlinks D Bauer – 2007 – cogsci.uni-osnabrueck.de … But many language technology appli- cations could profit from a domain independent knowledge base as a source of world knowledge (eg dialog systems and question answering systems, but also text generation, summarization and machine translation). … Cited by 1 Related articles All 17 versions

[PDF] from psu.edu [PDF] Automatic sentence structure annotation for spoken language processing DL Hillard – 2008 – Citeseer … features reflecting pause, duration, pitch, energy, and speaker change information. The prosody model is a decision tree classifier that generates the posterior probability of an SU boundary at each inter-word boundary given the prosodic features. … Cited by 7 Related articles All 15 versions

[PDF] from velldal.net [BOOK] Empirical realization ranking E Velldal – 2008 – velldal.net Page 1. University of Oslo Department of Informatics Empirical Realization Ranking Erik Velldal A thesis submitted for the degree of philosophiae doctor (Ph.D.) December, 2007 Page 2. Page 3. Abstract This thesis develops … Cited by 19 Related articles All 5 versions

[PDF] from tut.fi Multilingual Text-to-Speech System for Mobile Devices: Development and Applications K Pärssinen – … teknillinen yliopisto. Julkaisu-Tampere University of …, 2007 – dspace.cc.tut.fi Page 1. Julkaisu 662 Publication 662 Kimmo Pärssinen Multilingual Text-to-Speech System for Mobile Devices: Development and Applications Tampere 2007 Page 2. Tampereen teknillinen yliopisto. Julkaisu 662 Tampere University of Technology. Publication 662 … Cited by 1 Related articles All 2 versions

[PDF] from zcu.cz [PDF] Automatic segmentation of speech into sentence-like units J Kolár – 2008 – mde.zcu.cz Page 1. University of West Bohemia in Pilsen Faculty of Applied Sciences AUTOMATIC SEGMENTATION OF SPEECH INTO SENTENCE-LIKE UNITS Ing. Jáchym Kolár A dissertation submitted for the degree of Doctor of Philosophy in Cybernetics Major Advisor: Prof. Ing. … Cited by 5 Related articles All 11 versions

[PDF] from ohio-state.edu [PDF] Noun phrase generation for situated dialogs L Stoia – 2007 – slate.cse.ohio-state.edu … Page 2. Page 3. ABSTRACT Modern dialog systems present significant challenges for developing algorithms … system take advantage of the user’s possibility of movement to facilitate descriptions (3) evaluation: algorithms for situated dialog systems are by nature very hard to … Cited by 4 Related articles All 9 versions

[PDF] from uni-stuttgart.de [PDF] Analysis and visualization of coreference features SW Kessler – 2010 – ims.uni-stuttgart.de … Such a link-based classification system is the decision tree classifier used by Soon [SNL01] and later Ng and Cardie [NC02]. But coreference resolution can also be viewed as a clustering task. Clustering is an unsuper- vised learning method. … Related articles All 3 versions

[PDF] from utexas.edu [BOOK] Learning for semantic parsing and natural language generation using statistical machine translation techniques YW Wong – 2007 – books.google.com … 9 Page 26. with various hypothetical travel planning scenarios to solve. The resulting spon- taneous spoken queries were recorded as the subjects interacted with automated dialog systems to solve the scenarios. The recorded … Cited by 7 Related articles All 23 versions

[PDF] from psu.edu [PDF] Enhancing hypernym extraction for named entities using machine learning based classification A Faulhaber – 2005 – Citeseer Page 1. Enhancing hypernym extraction for named entities using machine learning based classification Bachelor’s thesis at the Institute of Computer Science at the Faculty of Mathematics and Computer Science of the University of Heidelberg by Arndt Faulhaber August 2005 … Related articles All 3 versions

[PS] from cmu.edu [PS] Oriented Conversations from the Corpus A Chotimongkol – 2005 – cs.cmu.edu … iii Abstract Acquiring domain-specific knowledge necessary for creating a dialog system in a new task- oriented domain is a time consuming task which also requires domain expertise. … The example of such situation is building a dialog system in a military domain. … Related articles All 2 versions

[PDF] from utwente.nl On the structuring of discussion transcripts based on utterances automatically classified AT Verbree – 2006 – essay.utwente.nl Page 1. On the Structuring of Discussion Transcripts Based on Utterances Automatically Classified AT Verbree Master of Science Thesis Computer Science Research Group Human Media Interaction Faculty of Computer Science University of Twente Enschede, The Netherlands … Cited by 7 Related articles All 3 versions

[PDF] from washington.edu [PDF] Moving beyond the lexical layer in parsing conversational speech JG Kahn – 2005 – crow.ee.washington.edu Page 1. Moving Beyond the Lexical Layer in Parsing Conversational Speech Jeremy Gillmor Kahn A thesis submitted in partial fulfillment of the requirements for the degree of Master of Arts University of Washington 2005 Program Authorized to Offer Degree: Linguistics Page 2. … Cited by 7 Related articles All 9 versions

[PDF] from washington.edu [PDF] Segmentation and Feature Selection for Conversational Speech Syntactic Language Models WP McNeill – 2006 – ssli.ee.washington.edu … This is an interesting challenge in its own right and a precondition for downstream applications such as speech-based extraction and summarization and human-computer dialog systems. This thesis describes a system that uses syntactic models to improve the accu- … Related articles All 2 versions

[PDF] from leidenuniv.nl [BOOK] Flat but not shallow: towards flatter representations in deep semantic parsing for precise and feasible inferencing HHGB Reckman – 2009 – openaccess.leidenuniv.nl … this thesis. The project aims at the development of a natural language dialogue system that discloses personal narratives to facilitate patients (and their relatives) in finding relevant experiences of their fellow patients. The system … Related articles All 5 versions

[TXT] from tdx.cat [BOOK] Combining machine learning and rule-based approaches in Spanish syntactic generation MT Melero Nogués – 2006 – tdx.cat … 2. In the second part we explore the use of Decision Tree classifiers (DT) for automatically learning one of the operations that take place in the Pre-Generation component … 11 On the other hand, other applications such as data mining, text summarization, dialogue systems, etc. … Cited by 5 Related articles All 11 versions