Báo cáo khoa học: "Optimising Information Presentation for Spoken Dialogue Systems" pdf

... 2009.A wizard-of-oz interface to study information pre-sentation strategies for spoken dialogue systems. InProc. of the 1st International Workshop on Spoken Dialogue Systems.Crystal Nakatsu. 2008. ... 1009–1018,Uppsala, Sweden, 11-16 July 2010.c2010 Association for Computational LinguisticsOptimising Information Presentation for Spoken Dialogue SystemsVerena RieserUniversity of EdinburghEdinburgh, ... Trainable sentence planning for complex in-formation presentation in spoken dialog systems. InAssociation for Computational Linguistics.R. Sutton and A. Barto. 1998. Reinforcement Learn-ing. MIT...

Tài liệu Báo cáo khoa học: "Towards Relational POMDPs for Adaptive Dialogue Management" pdf

... IntroductionThe development of spoken dialogue systems for rich, open-ended interactions raises a number ofchallenges, one of which is dialogue management.The role of dialogue management is to determinewhich ... 2010.c2010 Association for Computational LinguisticsTowards Relational POMDPs for Adaptive Dialogue ManagementPierre LisonLanguage Technology LabGerman Research Centre for Artiﬁcial Intelligence ... uniﬁedframework for adaptive dialogue management inrich, open-ended interactional settings.This paper is structured as follows. Section 2lays down the formal foundations of our work,by describing dialogue...

Báo cáo khoa học: "MATCH: An Architecture for Multimodal Dialogue Systems" ppt

... sub-way information for New York City.1 Multimodal Mobile Information AccessIn urban environments tourists and residents alikeneed access to a complex and constantly changingbody of information ... Users can ask for information about restaurants, such as phone numbers, addresses,and reviews. For example, a user might circle threerestaurants as in Figure 3 and say phone numbers for these three ... informa-tion about required and optional roles for differenttypes of actions); if it is not, then the system’s nextmove is to take the initiative and start an information- gathering subdialogue....

Báo cáo khoa học: "Classifying Recognition Results for Spoken Dialog Systems" doc

... sub-stitutions). (1) shows two possible alignments for arecognized utterance from the ATIS2 corpus, where‘m’ stands for match, ‘i’ for insertion, and ‘s’ for substitution.(1) Ambiguous Levenstein ... the results for the NUANCE recognizer on the test set were 66and 43.3.3 ML ClassiﬁcationWe computed a feature vector representation for each recognition result which served as input for the two ... Recognizer Statistics: 85. Site Information: 06. f0 Statistics: 37. RMS Statistics: 2Table 6: Features used by RipperWe can see that all feature groups except “Site Information contribute to the...

Báo cáo khoa học: "Stochastic Discourse Modeling in Spoken Dialogue Systems Using Semantic Dependency Graphs" pdf

... method, a spoken dialogue system for medical domain with multiple services was investigated. Three main services: registration information service, clinic information service, and FAQ information ... understanding in the spoken dialogue systems. Five main catego-ries about medical application, clinic information, Dr.’s information, confirmation for the clinic in-formation, registration ... accuracy for speech act identification 942 For example, the user may only say “yes” or “no” for confirmation. The misclassification in speech act will happen due to the limited information. ...

Báo cáo khoa học: "Semantic Information Preprocessing for Natural Language Interfaces to Databases" docx

... predicates). Output is a logical formula, consisting of predicates meaningful to the database engine (database predicates). AET provides a formalism for describing how a formula consisting of lexical ... equivalences is a conjunction of atomic formulas rather than arbitrary formula. We demand that an RLDT be nonrecursive. In- formally RLDT nonrecursivness means that for any set of facts A, if there ... how a formula consisting of lexical predicates can be tranlsated into formula consisting of database predicates. The information used in the translation process is an LDT. A theory r contains...

Tài liệu Báo cáo khoa học: "Minimum Cut Model for Spoken Lecture Segmentation" ppt

... representing nodes, the threshold distances for discarding node edges, the number of uniformchunks for estimating tf-idf lexical weights, thealpha parameter for smoothing, and the length ofthe smoothing ... the segments correspondto presentation slides for the lectures.Due to the low recording quality, we were un-able to obtain the ASR transcripts for this class.Therefore, we only use manual transcriptions ... due to specialized technical vocabularyand lack of in-domain spoken data for training.Finally, pedagogical considerations call for ﬂuenttransitions between different topics in a lecture,further...

Tài liệu Báo cáo khoa học: "Re-Usable Tools for Precision Machine Translation∗" pdf

... Boks 1080 Blindern; 0316 Oslo (Norway)♠Center for the Study of Language and Information, Stanford, CA 94305 (USA){ jtl@ifi.uio.no| oe@csli.stanford.edu}AbstractThe LOGON MT demonstrator assemblesindependently ... Norwegian Research Council program for building national infrastructure for languagetechnology (Fenstad et al., 2006). It is the goal for the program as well as for the project to in-clude various ... of the COLING/ACL 2006 Interactive Presentation Sessions, pages 53–56,Sydney, July 2006.c2006 Association for Computational LinguisticsRe-Usable Tools for Precision Machine Translation∗Jan...

Tài liệu Báo cáo khoa học: "Resume Information Extraction with Cascaded Hybrid Model" pdf

... as Personal Information, Education etc. Then within each general information block, detailed information pieces can be found, e.g., in Personal Information block, detailed information such ... shown in Table 1, 7 general information fields are defined. Then, for Personal Information, 14 detailed information fields are designed; for Education, 4 detailed information fields are designed. ... HMM for the educational detailed information extraction for the same reason. In addition, classification based method is selected for the personal detailed information extraction where information...

Tài liệu Báo cáo khoa học: "A Writing Assistant for CAT and CALL" pdf

... parts-of-speech for syntactic generalization. Secondly, we build up inverted files of the words in Ct for the next stage (i.e., pattern grammar generation). Apart from sentence and position information, ... the Association for Computational Linguistics, pages 16–19,Avignon, France, April 23 - 27 2012.c2012 Association for Computational LinguisticsTransAhead: A Writing Assistant for CAT and CALL ... segmentation for MT and to complete the translation. Note that a user vocabulary of preference (due to users’ domain of knowledge or errors of the system) may be exploited for better system performance....

Xem thêm