Báo cáo khoa học: "Personality Generation for Dialogue" ppt

... 496–503,Prague, Czech Republic, June 2007.c2007 Association for Computational LinguisticsPERSONAGE: Personality Generation for DialogueFranc¸ois MairesseDepartment of Computer ScienceUniversity ... comparisons in the restaurant domain, for adatabase of restaurants in New York City. Thereare eight attributes for each restaurant: the name andaddress, scalar attributes for price, food quality, at-mosphere, ... parameters for different aspectsof sentence planning discussed below.4.1 Syntactic template selectionPERSONAGE’s input generation dictionary is madeof 27 Deep Syntactic Structures (DSyntS): 9 for the...

Báo cáo khoa học: "An Architecture for Dialogue Management, Context Tracking, and Pragmatic Adaptation in Spoken Dialogue Systems" pot

... back-end command Waveform :: : Text striri[ ~ ."~ Logical form (with dependent references) Logical form Text string: : :~: ,: : Lo~ic~ form, /~,,, Logical form (with dependent ... section 1.1) based on its own protocol for interaction. Back-end response Logical form (w/out dependent references) Various Logical form Logical form (conditioned by discourse context) ... components can consult in order to (a) resolve dependent forms that occur in input utterances and (b) gen- erate appropriate context-dependent forms for achieving natural output. Interpretation of...

Báo cáo khoa học: "Using Generation for Grammar Analysis and Error Detection" pptx

... thatit can be used for both parsing (interpreting textinto semantics) and generation (realizing seman-tics as text). Since both parsing and generation usethe same grammar, their performance is closelyrelated: ... practicethis is not always true. For example, to improveperformance, semantically empty lexemes are notinserted into a generation unless a “trigger-rule”deﬁnes a context for them. These trigger-rulesmay ... system istested on two implemented HPSG gram-mars: Jacy for Japanese, and the ERG for English. Using this system, we were ableto increase generation coverage in Jacy by18% (45% to 63%) with only...

Tài liệu Báo cáo khoa học: "A MODEL FOR PREFERENCE" ppt

... no formal or linguis- tic guarantee that this will be the case for the relation as a whole or for the translation steps between inter- mediate levels of representation. (An attempt to formalize ... to calculate a global score for a representation seems a rather arbitrary procedure. Such a uniform metric, even if it can model actual linguistic knowledge, forces the grammar writer to ... true synonymy in generation) . ii accidental, caused by overgeneration of the descriptive devices that define the resulting (or intermediate) interpreta- tions. Note that overgeneration and...

Báo cáo khoa học: "Deep Learning for NLP" pptx

...

Báo cáo khoa học: "Non-Cooperation in Dialogue" pptx

... detailbefore the House of Commons andbefore the select committee.UCTable 2 summarises non-cooperative features,utterances and the degree of non-cooperation for each participant and for the ... associated force andpropositional content. Going back to Heritage’scomment, in a political interview participants canfail to restrict their speech acts to the force andcontent expected for their ... non-cooperative features present in thedialogue and establish a formalisable framework for approaching non-cooperative dialogue.As for the domain, the wealth of interesting con-versational situations...

Tài liệu Báo cáo khoa học: "Resumption strategies for an in-vehicle dialogue system" ppt

... That means that the most common rea-son for the speaker to interrupt is to ask for or giveinformation that is crucial for the driving task (asopposed for the other and trafﬁc domains, whichare ... inter-ruption. We therefore sorted all utterances coded800as resume-topic in two categories, those whichcontained redundant information when comparingwith the last utterance before the interruption, ... navigation instructions andtherefore is the one that is forcing both the inter-view and the navigation task through.4.3 Workload levelThe in-vehicle environment is forcing the driver tocarry...

Tài liệu Báo cáo khoa học: "An Affect-Enriched Dialogue Act Classification Model for Task-Oriented Dialogue" doc

... (FACS) (2nd ed.). New York: Oxford University Press. K. Forbes-Riley, M. Rotaru, D.J. Litman, and J. Tetreault. 2007. Exploring affect-context depend-encies for adaptive system development. ... Association for Computational Linguistics, pages 1190–1199,Portland, Oregon, June 19-24, 2011.c2011 Association for Computational LinguisticsAn Affect-Enriched Dialogue Act Classification Model for ... con-fusion. The findings indicate that the affect-enriched classifiers perform significantly bet-ter for distinguishing user requests for feed-back and grounding dialogue acts within textual dialogue....

Tài liệu Báo cáo khoa học: "Multimodal Generation in the COMIC Dialogue System" docx

... Association for Computational LinguisticsMultimodal Generation in the COMIC Dialogue SystemMary Ellen Foster and Michael WhiteInstitute for Communicating and Collaborative SystemsSchool of Informatics, ... creates logical forms as input for theOpenCCG surface realiser. The logical forms mayinclude explicit alternatives in cases where there aremultiple ways of expressing a property; for exam-ple, ... module needs the timing in-formation from the speech synthesiser to ﬁnalise theschedules for the other modalities, the synthesiserﬁrst prepares and stores the waveform for its inputtext; the...

Tài liệu Báo cáo khoa học: "Co-training for Predicting Emotions with Spoken Dialogue Data" pdf

... performance end end average_performance and keep average_performance end B = best average_performance bestFeatures  B ∪ bestFeatures end Figure 2. Implemented algorithm for forward ... saved for later experiments. 4.1 Selecting the features The first task was to reduce the dimensionality and find the best set of features for maximizing the PPV for Emotional class and NPV for ... and 140 for the test set (used to measure the performance). The training set is randomly divided into two sets in each iteration of the algorithm: One for training and the other for development...

Xem thêm