... utterance, Htis the dialogue historical information, and Ω = {A 1, . . . , A q} is theset of DAs. Using the maximum approximation forsummation, (1) can be written as A ∗t= arg max A ΩWP ... under-standing (SLU) module converts Wtto an abstractrepresentation of the user’s dialogue act (DA). The dialogue management (DM) module determines theuser’s dialogue act A ∗tand accordingly ... INTERSPEECH, pages 268–271.C. Hori, K. Ohtake, T. Misu, H. Kashioka, and S. Naka-mura. 2009b. Statistical dialog management appliedto wfst-based dialog systems. In Proc. IEEE Inter-national Conference...
... Uncertainty in Spoken Tutorial Dialogue Systems. International Journal of Artificial Intelligence in Education, 16. C. Rich and C. L. Sidner. 1998. COLLAGEN: A Col-laboration Manager for Software ... tutoring task. In addition, the SIH is not always available and users have to activate it manually. Other visual improvements for dialogue- based computer tutors have been explored in the past (e.g. ... Tutor5362that naïve users can reliably annotate the informa-tion needed for the NM (Passonneau and Litman, 1993). Our NM design choices should also have an equivalent in a new domain (e.g. displaying...
... European Chapter of the Association for Computational Linguistics, pages 46–50,Avignon, France, April 23 - 27 2012.c2012 Association for Computational Linguistics A Statistical SpokenDialogue ... user goals adopted to make sys-tems computationally tractable.Work in dialoguesystem evaluation, e.g.Walker et al. (2004) and Lemon et al. (2006),shows that real user goals are generally sets ... Thomson and S. Young. 2010. Bayesian updateof dialogue state: A POMDP framework for spoken dialogue systems. Computer Speech and Language,24(4):562–588.Marilyn Walker, S. Whittaker, A. Stent,...
... 08540, USAusyed@cs.princeton.eduJason D. WilliamsShannon LaboratoryAT&T Labs — ResearchFlorham Park, NJ 07932, USAjdw@research.att.comAbstractWe use an EM algorithm to learn user ... expectation and itsmaximization are easy to compute. This is becauseour dialog model has a chain-like structure thatclosely resembles an Hidden Markov Model, so a forward-backward procedure can ... θ be the maximum likelihoodestimate using automatically transcribed data,i.e., θasu=eKDasP a eKDas. This approach ignorestranscription errors and assumes that user be-havior depends...
... management for spokendialogue systems. Finally, statistical modelling is prone to sparse data problems, and we need to consider ways to overcome inaccuracies in calculating mutual information. ... role and an inte- grated system must also produce a semantic analysis of the input utterance. Although the goal may be a shallow understanding only, it is not enough that the system knows that ... test utterances), and used the other 70 dialogues for training in each test cycle. The average accuracy rate, 78.68 % is a satisfactory result. We also did another set of cross-validation tests...
... efficient and natural access to applica-tions and services, such as email and calendars,travel and entertainment booking, and product rec-ommendation. In evaluating nine SDS in theDARPA Communicator ... designedmanually, as this system is implemented for an-other domain. The order of the dialogues in a pairwas randomized. The dialogues were provided astranscripts.After reading each dialogue transcript, ... important than for a user who does not careabout price).The explicit presentation of tradeoffs made bythe UMSR system in many cases leads to dialogue turns that are more complex than typical dialogue turns...
... machines. In HLT-03. R. Higashinaka, N. Miyazaki, M. Nakano, and K. Ai-kawa. 2004. Evaluating Discourse Understanding in Spoken Dialogue Systems. ACM Transactions on Speech and Language ... conver-sational speech. Computational Linguistics 26(3), 339 373. M. A. Walker, D. Litman, C. Kamm, and A. Abella, 1997. PARADISE: a general framework for evaluat-ing spokendialogue agents. ... such as semantic relation, semantic class and semantic role are adopted in the semantic dependency graph (Gildea and Jurasfky, 2002; Hacioglu and Ward, 2003). The semantic relations constrain...
... Computer-Human Interaction.(to appear).Oliver Lemon, Alexander Gruenstein, and StanleyPeters. 2002. Collaborative activities and multi-tasking in dialogue systems. Traitement Automa-tique des Langues, ... op-Combining Acoustic and Pragmatic Features to Predict RecognitionPerformance in SpokenDialogue SystemsMalte GabsdilDepartment of Computational LinguisticsSaarland UniversityGermanygabsdil@coli.uni-sb.deOliver ... http://www.talk-project.orgWalter Daelemans and V´eronique Hoste. 2002.Evaluation of Machine Learning Methods forNatural Language Processing Tasks. In Proceed-ings of LREC-02.Walter Daelemans, Jakub Zavrel, Ko van...
... with adialoguesystem is to use a grammar-based language model and assist usersin becoming expert as quickly as possible. Thisapproach takes advantage of the strengths of bothtypes of language ... deployed and tested as partof the WITAS dialogue system l , a command andcontrol and mixed-initiative dialoguesystem forinteracting with a simulated robotic helicopter orUAV (Unmanned Aerial ... interaction, adaptation andstyles of management, page (in press).Oliver Lemon, Anne Bracy, Alexander Gruenstein, andStanley Peters. 2001. Information states in a multi-modal dialogue system...
... 28:811–840.Marilyn Walker, Amanda Stent, Franc¸ois Mairesse, andRashmi Prasad. 2007. Individual and domain adap-tation in sentence planning for dialogue. Journal ofArtificial Intelligence Research (JAIR), ... Sutton and A. Barto. 1998. Reinforcement Learn-ing. MIT Press.Marilyn A. Walker, Candace A. Kamm, and Diane J.Litman. 2000. Towards developing general mod-els of usability with PARADISE. Natural ... IC-SLP.Amanda Stent, Rashmi Prasad, and Marilyn Walker.2004. Trainable sentence planning for complex in-formation presentation in spoken dialog systems. InAssociation for Computational Linguistics.R....
... the dialogue. We then calculate the overall mean accuracy overall referents as shown below.RAr=#(appropriate expressions(r))#(instances(r))AdaptationAccuracyAA =1#(r)ΣrRArNote that ... SpokenDialogue SystemsSrinivasan JanarthanamSchool of InformaticsUniversity of Edinburghs.janarthanam@ed.ac.ukOliver LemonInteraction LabMathematics and Computer Science (MACS)Heriot-Watt ... Current Research in NaturalLanguage Generation, pages 257–285. AcademicPress.V. Rieser and O. Lemon. 2009. Natural LanguageGeneration as Planning Under Uncertainty for Spo-ken Dialogue Systems....
... Saffrani, which is also an Indian restaurant, is in the moderate price range.COMPARE byAttributeThe restaurant called Kebab Mahal and the restaurant called Saffrani are both Indian restaurants.However, ... Compu-tational Linguistics (ACL).Marilyn Walker, Amanda Stent, Franc¸ois Mairesse, andRashmi Prasad. 2007. Individual and domain adap-tation in sentence planning for dialogue. Journal ofArtificial ... Workshop on Natural Language Generation(ENLG).Marilyn A. Walker, Candace A. Kamm, and Diane J.Litman. 2000. Towards developing general mod-els of usability with PARADISE. Natural LanguageEngineering,...
... Natural ~ Context 'Language Tracking aterpretation (on Input) Natural Language Generation Dialogue Manager Pragmatic Adaptation (on Input) Back-End " ~ Pragmatic Adaptation ... in Table 3. Dialogue with an Appliance Dialogue with an Application Dialogue with an Intelligent Robot Computer Mediation of Human Dialogue Computer Analysis of Human Dialogue ... In fact, it was first developed for bilingual dialogue in a voice-to-voice machine translation application. In this application, the Dialogue Manager is available for meta- dialogues with...
... of air travel planning. There is a large body of existing data in that domain (MADCOW, 1992), and speakers familiar with the domain are easily available. The internal representation of actions ... Formalisms. Computational Linguis- tics, 16(1), March. M. Walker, J. Fromer, and S. Narayanan. 1998. Learning Optimal Dialogue Strategies: A Case Study of aSpokenDialogue Agent for Email. In Proceedings ... utterance 22 is with a 154 The CommandTalk SpokenDialogue System* Amanda Stent, John Dowding Jean Mark Gawron, Elizabeth Owen Bratt, and Robert Moore SRI International 333 Ravenswood Avenue...