Active Learning & Dialog Systems


Active learning (machine learning)


Phrase-based statistical language generation using graphical models and active learning [PDF] from aclweb.org F Mairesse, M Gašic, F Jurcícek, S Keizer… – Proceedings of the 48th …, 2010 – dl.acm.org … each active learning iteration requires gen- erating all training utterances in our domain, they are generated using a larger clique pruning thresh- old than the test utterances used for evaluation. 5.1 Corpus collection We train BAGEL in the context of a dialogue system providing … Cited by 10 – Related articles – All 15 versions

Situated Spoken Dialogue with Robots Using Active Learning [PDF] from nict.go.jp K Sugiura, N Iwahashi, H Kawai… – Advanced …, 2011 – ingentaconnect.com … Keywords Active learning, confidence, robot language acquisition, object manipulation dialogue … In the field of spoken dialogue systems (SDS), the whether-to-confirm problem has received considerable attention in the context of error handling [3, 4]. The problem of how to … Related articles – All 2 versions

An Active Learning Approach for Statistical Spoken Language Understanding F García, LF Hurtado, E Sanchis… – Progress in Pattern …, 2011 – Springer … Spoken Dialog System. Some experiments that show the appropriateness of our approach are also presented. Keywords: active learning, unaligned corpus, spoken language under- standing, spoken dialog systems. 1 Introduction …

Active learning and semi-supervised learning for speech recognition: A unified framework using the global entropy reduction maximization criterion [PDF] from microsoft.com D Yu, B Varadarajan, L Deng… – Computer Speech & Language, 2010 – Elsevier … We would like to point out that using a global criterion for active learning has also been explored by Kuo and Goel (2005) for the dialog system upon the error rate reduction approaches. Different from their approach, our approach … Cited by 3 – Related articles – All 7 versions

[PDF] Reciprocal Learning via Dialogue Interaction: Challenges and Prospects [PDF] from utexas.edu R Fernández, S Larsson, R Cooper, J Ginzburg… – 2011 – cs.utexas.edu … From the dialogue systems research commu- nity, we are making first steps in this direction … Learning techniques such as one-shot learning, bootstrap learning, and active learning [Fei-Fei et al., 2006; Modayil and Kuipers, 2007; Chao et al., 2010] might be able to open the door … Related articles – View as HTML – All 5 versions

D3 toolkit: a development toolkit for daydreaming spoken dialog systems [PDF] from postech.ac.kr D Lee, K Kim, C Lee, J Choi… – Spoken Dialogue Systems for …, 2010 – Springer … toolkit starts from loading a set of log files which have been generated when the real users talked to the dialog system in the … The developer is only required to verify and modify auto-generated candidates like active learning [7]. New utterance patterns are added to the existing … Related articles – All 5 versions

Predicting Learning Styles in a Conversational Intelligent Tutoring System A Latham, K Crockett, D McLean… – Advances in Web-Based …, 2010 – Springer … When compared to the ILS questionnaire results, Oscar accurately predicted an Active learning style in 100% of cases, however it was not possible to predict a Reflective … 363-367 (2007) [19] Litman, DJ, Silliman, S.: ITSPOKE: An intelligent tutoring spoken dialogue system. … Cited by 5 – Related articles – All 2 versions

[PDF] Real user evaluation of spoken dialogue systems using Amazon Mechanical Turk [PDF] from mit.edu F Jurcicek, S Keizer, M Gašic… – Proceedings of …, 2011 – people.csail.mit.edu … ASRU, 2009. [3] M. Geist and O. Pietquin, “Managing Uncertainty within the KTD Framework,” in Proceedings of the Workshop on Active Learning and Experimental Design, Sardinia, Italy, 2011. [4] J. Schatzmann, “Statistical user modeling for dialogue systems,” Ph.D … Cited by 4 – Related articles – View as HTML – All 2 versions

[PDF] Active Learning for Building a Corpus of Questions for Parsing [PDF] from lrec-conf.org J Atserias, G Attardi, M Simi… – Corpus, 2010 – lrec-conf.org … for improving the accuracy of parsers but also in other high level natural language tasks which involve analyzing questions (eg question answering, Frequently Asked Questions retrieval, dialog systems, etc). We have also shown that different active learning strategies, albeit … Cited by 2 – Related articles – View as HTML – All 2 versions

Active Learning D Hakkani-Tür… – Spoken Language Understanding, 2011 – Wiley Online Library Page 1. 8 Active Learning Dilek … components. In this chapter, we review machine learning algorithms for example selections, so-called active learning methods, and describe relevant spoken language processing applications. 8.1 Introduction … Related articles

Active Learning for Generating Motion and Utterances in Object Manipulation Dialogue Tasks [PDF] from nict.go.jp K Sugiura, N Iwahashi, H Kawai… – Proceedings of the 2010 …, 2010 – aaai.org … One of the contributions of this study is the in- troduction of active learning into a multimodal spoken dialogue system. Some demo video clips can be found at http://mastarpj.nict.go.jp/˜ ksugiura/ video_gallery/video_gallery_en.html. References Bohus, D., and Rudnicky, A. 2005. … Related articles – All 5 versions

[PDF] Managing uncertainty within the ktd framework [PDF] from mit.edu M Geist… – … of the Workshop on Active Learning and …, 2010 – jmlr.csail.mit.edu … section, we present several approaches designed to handle the dilemma between exploration and exploitation (which can be linked to active learning). … A spoken dialog system (SDS) generally aims at providing information to a user through natural language-based interactions. … Cited by 7 – Related articles – View as HTML

[PDF] A Bayesian Method for Learning POMDP Observation Parameters for Robot Interaction Management Systems [PDF] from utl.pt A Atrash… – The POMDP Practitioners Workshop, 2010 – users.isr.ist.utl.pt … An example of this occurs because the dialogue system essentially resets itself after each completed action. … Active learning (Cohn, Ghahramani, and Jordan 1995) has also been explored as a method for learning probabilis- tic models. … Cited by 2 – Related articles – View as HTML – All 2 versions

Active learning for dialogue act labelling F Ghigi, V Tamarit, CD Martínez-Hinarejos… – Pattern Recognition and …, 2011 – Springer … A dialogue system is usually defined as a computer system that interacts with a human by using dialogue to achieve a defined objec- tive … The goal of this work is to explore various sample selection criteria and em- ploy them in an active learning strategy framework for dialogue … Cited by 1 – Related articles – All 2 versions

Active learning of confidence measure function in robot language acquisition framework K Sugiura, N Iwahashi, H Kashioka… – Intelligent Robots and …, 2010 – ieeexplore.ieee.org … In this paper, we proposed a method that decreases the risk of motion failure in the learning phase. One of the contributions of this study is the introduction of active learning into a multimodal spoken dialogue system. Some demo video clips can be found … Cited by 2 – Related articles – All 2 versions

Real User Evaluation of Spoken Dialogue Systems Using Amazon Mechanical Turk F Jurcícek, S Keizer, M Gašic… – … Annual Conference of …, 2011 – isca-speech.org … ASRU, 2009. [3] M. Geist and O. Pietquin, “Managing Uncertainty within the KTD Framework,” in Proceedings of the Workshop on Active Learning and Experimental Design, Sardinia, Italy, 2011. [4] J. Schatzmann, “Statistical user modeling for dialogue systems,” Ph.D …

Gaussian processes for fast policy optimisation of pomdp-based dialogue managers [PDF] from aclweb.org M Gašic, F Jurcícek, S Keizer, F Mairesse… – Proceedings of the 11th …, 2010 – dl.acm.org … 2.2 Voice Mail Dialogue Task In order to demonstrate how this methodology can be applied to a dialogue system, we first ex- plain the idea on the voice mail dialogue … 3.3 Active Learning GP-Sarsa The GP RL framework enables modelling the uncertainty of the approximation. … Cited by 5 – Related articles – All 12 versions

[PDF] Uncertainty management for on-line optimisation of a POMDP-based large-scale spoken dialogue system [PDF] from supelec.fr L Daubigney, M Gašic, S Chandramohan, M Geist… – 2011 – metz.supelec.fr … This is an instantiation of active learning where the utility function uses uncertainty in- formation [13]. … The use of GP-SARSA for fast learning in spoken dialogue systems was first described in [11] and the same system is used here. … Cited by 2 – Related articles – View as HTML – All 2 versions

[PDF] Learning from student responses: A domain-independent natural language tutor [PDF] from aclweb.org J McDonald, A Knott, R Zeng… – Workshop, pages, 2011 – aclweb.org … E 1 indicates low con- fidence and less difference between the class rank- ings. Finally the classifier is serialised, along with its associated feaureset parameters and saved for use in the dialogue system itself. 5 Testing classifiers … 2003. Inter- active learning systems evaluation. … View as HTML

[BOOK] Reinforcement Learning for Adaptive Dialogue Systems: A Data-driven Methodology for Dialogue Management and Natural Language Generation V Rieser… – 2011 – books.google.com Page 1. Theory and Applications of Natural Language Processing Monographs Verena Rieser Oliver Lemon Reinforcement Learning for Adaptive Dialogue Systems A Data-driven Methodology for Dialogue Management and Natural Language Generation Page 2. …

Sample efficient on-line learning of optimal dialogue policies with kalman temporal differences [PDF] from archives-ouvertes.fr O Pietquin, M Geist… – International Joint Conference …, 2011 – aaai.org … In Journal of Machine Learning Re- search, Workshop & Conference Proceedings (JMLR W& CP): Active Learning and Experimental Design, Sardinia, Italy, 2010. … Natural Belief-Critic: a reinforcement algorithm for pa- rameter estimation in statistical spoken dialogue systems. … Cited by 5 – Related articles – All 8 versions

A classifier-based approach to supporting the augmentation of the question-answer database for spoken dialogue systems H Narimatsu, M Nakano… – Spoken Dialogue Systems for …, 2010 – Springer … This paper concerns a kind of spoken dialogue system that answers user ques- tions by retrieving answers from a database consisting of a set … This can be regraded as a kind of active learning [6,2]. To better estimate the scores, the classifier uses various features obtained from … Cited by 1 – Related articles – All 3 versions

The EducAgent Platform: Intelligent Conversational Agents for E-Learning Applications D Griol, J García-Herrero… – Ambient Intelligence-Software and …, 2011 – Springer … a flexible learning tool to offer the stimulus, support and environment nec- essary to guide students in a continuous and active learning process. … 10(3), 814 (2006) 4. Griol, D., Hurtado, L., Segarra, E., Sanchis, E.: A Statistical Approach to Spoken Dialog Systems Design and … Related articles – All 2 versions

Spoken language understanding using weakly supervised learning WL Wu, RZ Lu, JY Duan, H Liu, F Gao… – Computer Speech & …, 2010 – Elsevier … Keywords: Spoken language understanding; Spoken dialogue system; Topic classification; Active learning; Self-training; Bootstrapping. Article Outline. 1. Introduction; 2. Related works; 2.1. The rule-based approaches; 2.2. The data-driven approaches; 2.3. … Cited by 7 – Related articles – All 5 versions

[PDF] D1. 5: Online adaptation of dialogue systems [PDF] from classic-project.org F Jurcicek, M Gašic, S Young, R Laroche, G Putois… – 2011 – classic-project.org … In Pro- ceedings of the Workshop on Active Learning and Experimental Design (AL&E collocated with AISTAT 2010), Journal of Machine Learning Research … Natural Belief-Critic: a reinforcement algorithm for parameter estimation in statistical spoken dialogue systems. … Related articles – View as HTML

Tutor-based learning of visual categories using different levels of supervision M Fritz, GJM Kruijff… – Computer Vision and Image …, 2010 – Elsevier Related articles – All 3 versions

Robot self-initiative and personalization by learning through repeated interactions [PDF] from archives-ouvertes.fr M Mason… – Proceedings of the 6th international conference …, 2011 – dl.acm.org … 2. DIALOG SYSTEM A dialog system is used to receive the users’ commands and clarification responses and to provide cooperative super- vision of the task execution. … 5.2 Dialog System The Dialog system is implemented using the Nuance SDK [17]. … Cited by 3 – Related articles – All 5 versions

Rapid and inexpensive development of speech action classifiers for natural language call routing systems EE Jan… – Spoken Language Technology …, 2010 – ieeexplore.ieee.org … [4] Dilek Hakkani-Tur, Gokhan Tur, Mazin Rahim and Giuseppe Riccardi, “Unsupervised and active learning in automatic … P. Hunter, K. Dayanidhi and R. Pieraccini, “From rule-based to statistical grammars: Continuous improvement of large- scale spoken dialog systems” in Proc … Related articles

Key Issues for Personalized Learning Service Provision in Ubiquitous Learning Environments LY Li, YL Zheng… – Advanced Materials Research, 2011 – Trans Tech Publ … Wahlster and Kobsa defined a user model as “a knowledge source in a natural-language dialog system which contains explicit … Active learning can not detached from learners’ personal perceptions, understanding, reflection of current learning situations, and often depends on … Related articles

Making sense of mediated learning: Cases from small firms A Macpherson, A Kofinas, O Jones… – Management …, 2010 – mlq.sagepub.com … For example, those firms that have a more active ‘learning orientation’ show increased performance using both financial and non … The processes identified above-identity formation, discourse and dialogue, systems and routines, reflection, time and space, and politics and friction … Cited by 2 – Related articles – All 8 versions

Better to be frustrated than bored: The incidence, persistence, and impact of learners’ cognitive-affective states during interactions with three different computer-based … [PDF] from google.com RSJ Baker, SK D’Mello, MMT Rodrigo… – International Journal of …, 2010 – Elsevier … ITSs have emerged as valuable systems to promote active learning, with learning gains associated with sophisticated ITSs at around a 1.0 SD improvement (about a letter grade) when compared to controls (Dodds and Fletcher, 2004; Koedinger and Corbett, 2006; VanLehn et … Cited by 30 – Related articles – All 11 versions

Pedagogical Design and Evaluation of Interactive Information Retrieval Learning Environment K Halttunen – Teaching and Learning in Information Retrieval, 2011 – Springer … Instruction emphasizes active learning: doing and practicing. … Log files were downloaded from the QPA and converted into spreadsheets. Second, the Dialog system was used in the last search exercise session for the performance assessment of IR skills. … Related articles – All 2 versions

Semi-automated dialogue act classification for situated social agents in games [PDF] from mit.edu J Orkin… – Agents for games and simulations II, 2011 – Springer … 149 Fig. 1. Screenshot from The Restaurant Game Current approaches to implementing natural language dialogue systems in use in the video game industry are labor intensive, requiring designers to anticipate human input and hand-author responses. … Cited by 4 – Related articles – All 10 versions

[PDF] Growing a Spoken Language Interface on Amazon Mechanical Turk [PDF] from mit.edu I McGraw, J Glass… – Proc. Interspeech2011, Florence, 2011 – people.csail.mit.edu … 8(1), 2000. [13] A. Raux, D. Bohus, B. Langner, A. Black, and M. Eskenazi, “Do- ing research on a deployed spoken dialogue system: One year of Let’s Go! … [15] B. Varadarajan, D. Yu, L. Deng, and A. Acero, “Maximizing global entry reduction for active learning in speech … Cited by 1 – Related articles – All 3 versions

Benefits and challenges of real-time uncertainty detection and adaptation in a spoken dialogue computer tutor [PDF] from pitt.edu K Forbes-Riley… – Speech Communication, 2011 – Elsevier … We evaluate the performance of a spoken dialogue system that provides substantive dynamic responses to automatically detected user affective states. … This research is situated in the tutoring domain, where the user is a student and the spoken dialogue system is a tutor. … Cited by 5 – Related articles – All 4 versions

Pamini: A framework for assembling mixed-initiative human-robot interaction from generic interaction patterns [PDF] from sigdial.org J Peltason… – Proceedings of the 11th Annual Meeting of the …, 2010 – dl.acm.org … state pro- tocol supports robotic learning within interaction by establishing mechanisms for information trans- fer from the dialog system to the … Also, mixed-initiative enables active learning, where the learner provokes a situation providing new information instead of waiting un- til … Cited by 1 – Related articles – All 11 versions

Using crowdsourcing for labelling emotional speech assets [PDF] from dit.ie A Tarasov, SJ Delany… – 2010 – arrow.dit.ie … [7] A. Brew, D. Greene, and P. Cunningham. Using Crowdsourcing and Active Learning to Track Sentiment in Online Media. In Proc. … Influence of Contextual Information in Emotion Annotation for Spoken Dialogue Systems. Speech Communication, 50(5):416-433, 2008. … Cited by 3 – Related articles – All 2 versions

Sample-efficient batch reinforcement learning for dialogue management optimization [PDF] from supelec.fr O Pietquin, M Geist, S Chandramohan… – ACM Transactions on …, 2011 – dl.acm.org … widespread. Spoken Dialogue Systems (SDS) are such interfaces allowing people to interact with a computer or any other machine (like a robot) using speech, which is the most natural communication means for human beings. … Cited by 7 – Related articles – All 2 versions

Modeling human-robot interaction based on generic interaction patterns [PDF] from uni-bielefeld.de J Peltason… – AAAI Report on Dialog with Robots, 2010 – aaai.org … state protocol sup- ports learning within interaction by establishing mecha- nisms for information transfer from the dialog system to the … Moreover, mixed-initiative enables active learning, where the learner provokes a situation providing new information instead of waiting until … Cited by 4 – Related articles – All 6 versions

[PDF] Hierarchical reinforcement learning and hidden Markov models for task-oriented natural language generation [PDF] from aclweb.org N Dethlefs… – Proceedings of ACL-HLT 2011, Portland, OR, 2011 – aclweb.org … generation us- ing graphical models and active learning. In Proc. of the Annual Meeting of the Association for Computa- tional Linguistics (ACL), pages 1552-1561. Alice H. Oh and Alexander I. Rudnicky. 2000. Stochas- tic language generation for spoken dialogue systems. … Cited by 5 – Related articles – View as HTML – All 11 versions

Particle Swarm Optimization for Automatic Selection of Relevance Feedback Heuristics PY Yin – Advances in Swarm Intelligence, 2010 – Springer … Information retrieval techniques [1] have been intensively applied to many areas such as library dialog systems, database retrieval, web-based multimedia … Image Processing 9(1), 20-37 (2000) 8. Tong, S., Chang, EY: Support vector machine active learning for image retrieval. … Cited by 1 – Related articles

Human computation: a survey and taxonomy of a growing field [PDF] from alexquinn.org AJ Quinn… – Proceedings of the 2011 annual conference …, 2011 – dl.acm.org … Active learning In machine learning, classifiers are software modules that can be trained to recognize certain patterns in data (ie, outlines of common objects in an image, fraudulent credit card transactions, spoken words, etc.). … Cited by 39 – Related articles – All 5 versions

[PDF] Learning from Imbalanced and Incomplete Data: a Practical Approach [PDF] from cmu.edu W Chen – 2011 – cs.cmu.edu … Abstract This thesis deals with an important issue in tutorial dialog systems for children, namely off-task speech, wherein a user’s spoken input strays away from the intended tutorial activity. Off-task speech poses different levels of technical challenges to tutorial dialog systems. … Related articles – View as HTML

Online SLU model adaptation with a partial Oracle P Gotab, G Damnati, F Bechet… – … Annual Conference of …, 2010 – isca-speech.org … Deployed Spoken Dialog Systems (SDS) evolve quickly while new services are added or dropped, and while users’ be- haviour change. … This strategy, even when used with an active learning scheme, is costly as the transcription and annotation processes of the new collected … Cited by 2 – Related articles – All 3 versions

Reflection and learning robustness in a natural language conceptual physics tutoring system [PDF] from pitt.edu A Ward – 2010 – challenger.library.pitt.edu Page 1. REFLECTION AND LEARNING ROBUSTNESS IN A NATURAL LANGUAGE CONCEPTUAL PHYSICS TUTORING SYSTEM by Arthur Ward MBA, Carnegie Mellon University MS, Intelligent Systems, University of Pittsburgh Submitted to the Graduate Faculty of … Cited by 3 – Related articles – All 3 versions

Controlling user perceptions of linguistic style: Trainable generation of personality traits [PDF] from ucsc.edu F Mairesse… – Computational Linguistics, 2011 – MIT Press … There is growing evidence that dialogue systems such as intelligent tutoring systems are more effective if they can generate a range of different types of stylistic linguistic variation (Litman and Forbes-Riley 2004, 2006; Porayska-Pomsta and Mellish 2004; Wang et al. … Cited by 5 – Related articles – All 9 versions

Lessons Learned from Virtual Humans [PDF] from aaaipress.org W Swartout – AI Magazine, 2010 – aaai.org Page 1. The Institute for Creative Technologies was founded a decade ago to bring together researchers working at the cutting edge of simulation technologies, such as comput- er graphics, artificial intelligence, and virtual reality … Cited by 5 – Related articles – All 8 versions

Task-Oriented Spoken Dialogue System for Humanoid Robot Y Mu… – Multimedia Technology (ICMT), 2010 …, 2010 – ieeexplore.ieee.org … in humanoid robot developing, such as natural human-robot interaction, vision-based environment understanding and navigation, object grasping and manipulation based on dexterous hand, active learning of new … Development of spoken dialogue system requires a wide … Related articles

A Stochastic Finite-State Transducer Approach to Spoken Dialog Management LF Hurtado, J Planells, E Segarra… – … Annual Conference of …, 2010 – isca-speech.org … We are interested in the study of the behavior of our Di- alog Manager with real users, and in the application of active learning techniques to detect and to correct … [2] Y. Esteve, C. Raymond, F. Bechet, and RD Mori, “Conceptual Decoding for Spoken Dialog systems,” in Proc. … Cited by 3 – Related articles

Toward better crowdsourced transcription: Transcription of a year of the Let’s Go Bus Information System data [PDF] from universitypressclub.com G Parent… – Spoken Language Technology …, 2010 – ieeexplore.ieee.org … The Let’s Go Bus Information System is a spoken dialog system used nightly by the Port Authority of Allegheny County. … Active learning could then be achieved by retraining the ASR with the new data, thus improving accuracy and lowering the cost of MTurk by reducing the … Cited by 10 – Related articles – All 7 versions

Self-understanding and self-extension: A systems and representational approach [PDF] from bham.ac.uk JL Wyatt, A Aydemir, M Brenner… – Autonomous Mental …, 2010 – ieeexplore.ieee.org Page 1. 282 IEEE TRANSACTIONS ON AUTONOMOUS MENTAL DEVELOPMENT, VOL. 2, NO. 4, DECEMBER 2010 Self-Understanding and Self-Extension: A Systems and Representational Approach Jeremy L. Wyatt, Alper … Cited by 6 – Related articles – All 15 versions

Characteristic factors and components of different modules in expert systems for intelligent tutoring system K Mishra… – International Journal of Advanced Intelligence …, 2011 – Inderscience … Zhang et al. (2006) addressed the manual and automatic labelling of a particular type of user affect from spontaneous speech that they call the cognitive state in a tutorial dialogue system. … (2001) presented intelligent distributed environment for active learning (IDEAL), an … Related articles – All 6 versions

Still Talking to Machines (Cognitively Speaking) [PDF] from cam.ac.uk S Young – Eleventh Annual Conference of the International …, 2010 – isca-speech.org … This overview article reviews the structure of a fully statisti- cal spoken dialogue system (SDS), using as illustration, various systems and components built at Cambridge over the last few years. … The basic architecture of a statistical spoken dialogue system is shown in Fig. … Cited by 2 – Related articles – All 6 versions

The Art to Make an Error: The Dilemma Between Prevention, Learning and Mitigation K Bengler – Human Modelling in Assisted Transportation: Models, …, 2011 – Springer … In everyday life we can experience those systems in dialog system behavior of browsers. … to increase technical system deficits and make the system more error prone but to make the whole HMS more error robust based context information for an active learning intelligent user. … Related articles – All 2 versions

[PDF] Statistical Language Generation from Semantic Structures [PDF] from depling.org B Bohnet, S Mille… – Proceedings of the DepLing, 2011 – depling.org Page 1. Statistical Language Generation from Semantic Structures Bernd Bohnet1, Simon Mille2, Leo Wanner2,3 1 Institut für maschinelle Sprachverarbeitung (IMS) Universität Stuttgart, {first-name.last-name}@ims.uni-stuttgart … Cited by 2 – Related articles – View as HTML

Automatic committed belief tagging [PDF] from aclweb.org V Prabhakaran, O Rambow… – Proceedings of the 23rd …, 2010 – dl.acm.org … A dialog act repre- sents the communicative intention of the speaker, and its recognition is crucial for the building of dialog systems. … Another direc- tion we are looking to extend this work is to em- ploy active learning to overcome the shortcom- ings of a small training set. … Cited by 2 – Related articles – All 10 versions

Collecting and evaluating speech recognition corpora for 11 South African languages J Badenhorst, C van Heerden, M Davel… – Language resources and …, 2011 – Springer … There is a widespread belief that spoken dialog systems (SDSs) will have a significant impact in the developing countries of Africa (Tucker and … subsets of data from larger corpora, with the smaller subset yielding comparable results, and (3) the use of active learning to optimise … Cited by 2 – Related articles – All 4 versions

Memory-Based Learning [PDF] from ua.ac.be W Daelemans… – The Handbook of …, 2010 – Wiley Online Library … dialogue history features (eg, pre- vious dialogue acts), and acoustic features of recognized speech in the context of spoken dialogue systems. … the classifier needs to be retrained preferably with the availability of each new training example, eg, in active learning (Thompson et al … Related articles – All 5 versions

A comparison of active navigation and passive observation of desktop models of future built environments A Conniff, T Craig, R Laing… – Design Studies, 2010 – Elsevier Related articles

On the Use of N-Gram Transducers for Dialogue Annotation V Tamarit, CD Martínez-Hinarejos… – Spoken Dialogue Systems …, 2011 – Springer … Abstract The implementation of dialogue systems is one of the most interesting appli- cations of language technologies. … statistical models to obtain faster annotations is really interesting for the devel- opment of dialogue systems. … Related articles

[PDF] Automatically Optimizing Utterance Classification Performance without Human in the Loop [PDF] from microsoft.com YC Ju… – 2011 – research.microsoft.com … We also introduce two new algorithms that use naturally occurring confirmation information from the dialog system to provide ‘pseudo semantic … Future work includes applying active learning methods to select the best subset of the rejected utterances and the denied confirmation … Related articles – All 3 versions

Do You See What I Mean? Computer-Mediated Discourse Analysis [PDF] from dit.ie N Fitzpatrick… – 2010 – arrow.dit.ie … Levy, 1984; Rheingold, 1993). The educational potential was soon explored through early experimental dialogue systems, based on a ‘socratic dialogue’ methodology (Feurzeig, Munter, Swets, & Breen, 1964). The first analysis … Related articles – All 3 versions

[PDF] Defining (Human) Computation [PDF] from crowdresearch.org E Law – 2011 – crowdresearch.org … Princeton University Press, 2005. 5. Horvitz, E. and Paek, T. Complementary computing: policies for transferring callers from dialog systems to human receptionists. … http://rtw.ml. cmu.edu/rtw/. 8. Settles, B. Active Learning Literature Survey. Technical Report, 2009. … Related articles – View as HTML

Task transparency in learning by demonstration: gaze, pointing, and dialog [PDF] from gatech.edu NB dePalma – 2010 – smartech.gatech.edu … By providing a basic dialog system along with the first order task learning framework, task learning … of communication have advantages over batch learning [38], or that transparency in active learning improves performance [10]. … Related articles – Library Search

[BOOK] Spoken Language Understanding: Systems for Extracting Semantic Information from Speech G Tur, R De Mori – 2011 – books.google.com … Call Flow to POMDP: How Dialogue Management Integrates with SLU 7.4 Benchmark Projects and Data Sets 7.5 Time is Money: The Relationship between SLU and Overall Dialogue System Performance 7.6 Conclusion References Chapter 8: Active Learning 8.1 Introduction … Cited by 7 – Related articles – Library Search

[BOOK] Key issues in e-learning: research and practice N Pachler… – 2011 – books.google.com Page 1. Key Issues in e-Learning: Research and Practice Norbert Pachler and Caroline Daly Page 2. Page 3. Key Issues in e-Learning: Research and Practice Page 4. Also available from Continuum Key Ideas in Educational … Related articles – Library Search

WALTER DAELEMANS AND AVAN den BOSCH – The Handbook of Computational …, 2010 – books.google.com … dialogue history features (eg, pre- vious dialogue acts), and acoustic features of recognized speech in the context of spoken dialogue systems. … the classifier needs to be retrained preferably with the availability of each new training example, eg, in active learning (Thompson et al …

[BOOK] Proceeding of the 5th International Conference on ELearning: Universiti Sains Malaysia, Penang, Malaysia, 12-13 July 2010 I Ismail – 2010 – books.google.com … University, Palestine Assessing Online Textual Feedback to Support Student Intrinsic Motivation Using a Collaborative Text-Based Dialogue System: A Qualitative … As part of her work for the Centre for Excellence in Teaching and Learning-Active Learning in Computing at Leeds …

Multimodal semi-automated affect detection from conversational cues, gross body language, and facial features [PDF] from google.com SK D’Mello… – User Modeling and User-Adapted Interaction, 2010 – Springer … ITSs have emerged as valuable systems to promote active learning by capitalizing on the benefits of one-on-one tutoring in an automated fashion (Dodds and Fletcher 2004; Koedinger and Cor- bett 2006; VanLehn et al. 2007). … Cited by 33 – Related articles – All 7 versions

A POMDP approach to P300-based brain-computer interfaces [PDF] from kaist.ac.kr J Park, KE Kim… – Proceedings of the 15th international conference …, 2010 – dl.acm.org Page 1. A POMDP Approach to P300-Based Brain-Computer Interfaces Jaeyoung Park Dept. of Computer Science KAIST Daejeon, Korea jypark@ai.kaist.ac.kr Kee-Eung Kim Dept. of Computer Science KAIST Daejeon, Korea kekim@cs.kaist.ac.kr Sungho Jo Dept. … Cited by 3 – Related articles – All 4 versions

Semi-supervised ranking for document retrieval K Duh… – Computer Speech & Language, 2011 – Elsevier … Figures/Tables. Figures/Tables – selected. References. References – selected. Computer Speech & Language Volume 25, Issue 2, April 2011, Pages 261-281 Language and speech issues in the engineering of companionable dialogue systems. … Cited by 4 – Related articles – All 4 versions

Data-driven computational linguistics at FaMAF-UNC, Argentina [PDF] from aclweb.org G Infante-Lopez – Proceedings of the NAACL HLT 2010 Young …, 2010 – dl.acm.org … Luciana Benotti, investigates the addition of pragmatic abilities into dialogue systems. … How- ever, we have hopes that a more insightful charac- terization of the examples and smarter learning tech- niques (semi-supervised, active learning) will im- prove the results for these … Related articles – All 7 versions

[PDF] Statistical Dialogue Modelling [PDF] from cam.ac.uk M Gašic – 2011 – mi.eng.cam.ac.uk … 1 1.1.1 Spoken dialogue system structure . . . . . 3 1.1.2 Dialogue management . . . . . … 122 6.2.5 GP-Sarsa . . . . . 126 6.2.6 Active learning in Gaussian process reinforcement learn- ing . . . . . … Cited by 1 – Related articles – View as HTML

Exploration of student perceptions of autonomy, student-instructor dialogue and satisfaction in a web-based distance Russian language classroom: a mixed methods … [PDF] from uiowa.edu MV Kostina – 2011 – ir.uiowa.edu Page 1. University of Iowa Iowa Research Online Theses and Dissertations 2011 Exploration of student perceptions of autonomy, student-instructor dialogue and satisfaction in a web-based distance Russian language classroom: a mixed methods study … Related articles – All 2 versions

Multimodal fusion for multimedia analysis: a survey [PDF] from nus.edu.sg PK Atrey, MA Hossain, A El Saddik… – Multimedia Systems, 2010 – Springer … However, in general, these rules are domain specific and defining the rules requires proper knowledge of the domain. This fusion method is widely used in the domain of multimodal dialog systems and sports video analysis. 3.2 Classification-based fusion methods … Cited by 20 – Related articles – All 6 versions

[PDF] DETECTING OFF-TASK SPEECH [PDF] from cmu.edu W Chen – 2012 – cs.cmu.edu … robot cooperation. Off-task speech input to computers presents both challenges and opportunities for such dialog systems. … As a prevalent speech event, off- task speech has been acknowledged in many dialog systems, such as health communication … View as HTML

[BOOK] Tactile guidance for policy adaptation [PDF] from epfl.ch BD Argall, EL Sauser… – 2011 – books.google.com … Also available as a combined paper and online subscription. • Control of locomotion systems • Behaviour based systems • Distributed systems • Multi-Robot Systems • Human-Robot Interaction • Robot Safety • Physical Robot Interaction • Dialog Systems • Interface design … Cited by 4 – Related articles – All 9 versions

Compilation of References Compilation of References N Adamo-Villani, J Doublestein… – Virtual Immersive and 3D …, 2010 – books.google.com … 308-315), Trento, Italy, May 22-24, ACM Press. Christou, CG, & Bulthoff, HH (1999). View depen- dence in scene recognition after active learning. Memory & Cognition, 27 (6), 996-1007. Clark, K.(2002). Inspired 3D Character Animation. Portland, OR: Premier Press. 342 …

[PDF] A Decade Review of a Masters-Level Real-World-Projects Capstone Course [PDF] from isecon.org CC Tappert… – 2011 – proc.isecon.org … project. It is widely accepted that work in teams enhances learning by creating an “active learning process.” Student teams have been found particularly effective when the students actually need each other to complete the project. … Related articles – View as HTML – All 3 versions

[PDF] Project management and assessment of distributed teams in an online capstone masters-level information technology course [PDF] from pace.edu CC Tappert… – Proc. 6th International Conf. e-Learning, 2011 – csis.pace.edu … course the objective is to successfully complete a project. Research has shown that work in teams enhances learning by creating an “active learning process.” Student teams have been found particularly … ISECON 2005. J. Fu, “Design of Dialog Systems using VoiceXML,” Proc. … Cited by 1 – Related articles – View as HTML – All 2 versions

Speech Recognition by Machine, A Review [PDF] from arxiv.org MA Anusuya… – Arxiv preprint arXiv:1001.2267, 2010 – arxiv.org Page 1. (IJCSIS) International Journal of Computer Science and Information Security, Vol. 6, No. 3, 2009 Speech Recognition by Machine: A Review MAAnusuya Department of Computer Science and Engineering Sri Jaya chamarajendra College of Engineering Mysore, India . … Cited by 17 – Related articles – All 7 versions

[PDF] Multi-Modal Scene Understanding for Robotic Grasping [PDF] from kth.se J BOHG – 2011 – csc.kth.se … We consider multiple modalities including monocular and stereo vision, haptic sensing and information obtained through a human-robot dialog system. … 67 5.1 System Overview . . . . . 68 5.2 Dialog System . . . . . … View as HTML

[PDF] Elements for Learning and Optimizing Expensive Fuctions [PDF] from lri.fr P Rolet – 2010 – lri.fr … A key contribution of the present work is to formalize both active learning and optimization as Markov decision processes. … Dialogue systems An automated machine must interact with a user to acquire information and perform actions (eg interactive voice response for a … Cited by 1 – Related articles – View as HTML

MENON: automating a Socratic teaching model for mathematical proofs [PDF] from uni-saarland.de D Tsovaltzi – 2010 – scidok.sulb.uni-saarland.de … 45 1.2 The architecture of the prototype NL tutorial dialogue system of the Dialog project . . . . . … Moreover, the use of teaching strategies that abide by active learning is be- coming a prerequisite for tutoring systems. … Related articles – Library Search – All 4 versions

Human-Robot Interaction [PDF] from sagepub.com KS Jones… – Reviews of Human Factors and …, 2011 – rev.sagepub.com Page 1. CHAPTER 3 410388XXXXX10.1177/1557234X11410388Revie ws of Human Factors and Ergonomics, Volume 7Human-Robot Interaction Human-Robot Interaction: Toward Usable Personal Service Robots Keith S. Jones & Elizabeth A. Schmidlin … Related articles

Beyond Timbral Statistics: Improving Music Classification Using Percussive Patterns and Bass Lines E Tsunoo, G Tzanetakis, N Ono… – Audio, Speech, and …, 2011 – ieeexplore.ieee.org Page 1. Copyright (c) 2010 IEEE. Personal use is permitted. For any other purposes, Permission must be obtained from the IEEE by emailing pubs-permissions@ieee.org. This article has been accepted for publication in a future issue of this journal, but has not been fully edited. … Cited by 1 – Related articles – All 3 versions

Spoken Language Understanding: from Spoken Utterances to Semantic Structures [PDF] from unitn.it M Dinarelli – 2010 – eprints-phd.biblio.unitn.it … repeated until the application completes the modelled task. Spoken dialog systems need sophisticated SLU models in order to im- plement dialog applications that go beyond solving simple tasks like call … for named-entities extraction. An active-learning framework is integrated … Cited by 1 – Related articles

[PDF] Agreement Technologies Handbook Chapter Chapter on Norms (DRAFT) [PDF] from agreement-technologies.eu G Andrighetto… – 2011 – agreement-technologies.eu … These aspects can be explored further. Another limitation of current simulation-based works on norms is the lack of consideration of all the three aspects of active learning on the part of an agent (ie learning based on doing, observing and communicating). … View as HTML

[PDF] Mixed-Initiative Clustering [PDF] from psu.edu Y Huang – 2010 – Citeseer … The primitive communication languages in active learning would fail to assist a collaborative user in … If we want to embed natural language communication in mixed-initiative clustering, it is necessary to design a dialogue system capable of discussing a clustering task, but that … Related articles – View as HTML – All 5 versions

Un método de aprendizaje semi-supervisado para comprensión del habla [PDF] from upv.es L Ortega Álvarez – 2011 – riunet.upv.es … We applied this algorithm to the development of the understanding module of a spoken dialogue system, whose task is access to information about trains. … a percentage of smaller input sentences, later, through a process of active learning to be able …

[PDF] Reinforcement Learning Without Rewards [PDF] from princeton.edu UA Syed – 2010 – cs.princeton.edu … Similarly, in active learning, a very small number of emails are labeled in an incremental fashion, … the mentor’s behavior. We apply our method to the problem of modeling the behavior of users in a spoken dialog system, who typically behave in a goal-directed manner, … Related articles – View as HTML – Library Search – All 9 versions

[BOOK] Education and technology: key issues and debates N Selwyn – 2011 – books.google.com Page 1. Education and Technology Key Issues and Debates Neil Selwyn Page 2. Education and Technolo Key Issues and Debates Neil Selwyn Page 3. Education and Technology A companion website to accompany this book … Cited by 3 – Related articles – Library Search – All 2 versions

Identifying prosodic prominence patterns for English text-to-speech synthesis [PDF] from ed.ac.uk L Badino – 2010 – era.lib.ed.ac.uk … 122 5.4.4 Active Learning SVM for contrast labelling . . . . … Page 19. Chapter 1. Introduction 7 tences or when it is integrated within a dialogue system (usually working on limited domains, eg flight booking) that provides all the necessary contextual information to the TTS system. … Related articles

Éléments pour l’Apprentissage et l’Optimisation de Fonctions Chères [PDF] from archives-ouvertes.fr P Rolet – 2010 – tel.archives-ouvertes.fr … The first contribution was the conception and development of a new approach of active learning, based on reinforcement learning. … The second contribution is focused on the potential and limits of both active learning and expensive optimization, from a theoretical point of view. … Related articles – All 2 versions