... Czech Republic, June 2007.c2007 Association for Computational Linguistics PERSONAGE: PersonalityGenerationfor Dialogue Franc¸ois MairesseDepartment of Computer ScienceUniversity of SheffieldSheffield, ... parameters for different aspectsof sentence planning discussed below.4.1 Syntactic template selection PERSONAGE s input generation dictionary is madeof 27 Deep Syntactic Structures (DSyntS): 9 for the ... Second, Sections 3 and 4describe the PERSONAGE (PERSONAlity GEner-ator) generator and its 29 parameters. Table 1 showsexamples generated by PERSONAGEfor recom-mendations in the restaurant...
... the information in and outside the organization. Any information from any source can be useful, necessary for organizations as well as for members and volunteer activities in general. For example, ... classes for clubs. • Support clubs in terms of organization experience. 3.7. Backgrounds VIET NAM GREEN GENERATIONFOR A GREEN GLOBE PROPOSAL SUMMARY 1. Project Title: ‘Vietnam Green Generation ... globally-updated information and technology, foreign languages and up-to-date knowledge. On one hand, many volunteers groups are mushrooming to show their concern and care for social and environmental...
... DIKSIGN FOR I)IALOGUE COMPREHENSION William C. Mann USC Information Sciences Institute Marina del Rey, CA April, 1979 This paper describes aspects of the design of a dialogue comprehension ... llearsay-l[ and makes Preeminence Scheduling fairly straightforward. I. Dialogue Games, Speech Acts and DCS Examination of actual human dialogue reveals structure extending over • ~overal turns ... resolve. Our past work on dialogue has led to an account of this structure, Dialogue Game theory fLorin & Moore 1978; Moore, l,evlu & Mann 1977]. This theory claims that dialogues (and other...
... SATsolver [8, 10, 25]. First, for each atomic formula of the formx IS NULL we set the variable x to NULL, and then propagateNULL values through the formula. If the formula evaluatesto UNKNOWN, ... constraint solver for a satisfying assignment ¯s1of ϕ, then a satisfying assign-ment ¯s2 for ϕ∧¬[¯s1], then for ϕ∧¬[¯s1]∧¬[¯s2], etc. Iterating157Dynamic Test Input Generationfor Database ... the form δ1= δ2, δ1= δ2,or δ LIKE ρ, for atoms δ1and δ2, and regular expressionsρ. To do this normalization, we replace constraints of theform δ = s (respectively δ = s), for...
... target information during the measure word generation process. We do not integrate our measure word generation module into the SMT decoder since there is only little target contextual information ... quantity of objects. Therefore, in the English-to-Chinese machine translation task we need to take additional efforts to generate the missing measure words in Chinese. For example, when translating ... word with the highest probability will be chosen. There are two reasons why we perform measure word generationfor SMT systems as a post-processing step. One is that in this way our method can...
... lenient metric is applied for generating the gold standard for this collection. 5 An Opinion System CopeOpi A Chinese opinion extraction system for opinion-ated information, CopeOpi, is introduced ... this system’s performance is satisfac-tory, its behavior is not like human beings. For a computer system, the lenient testing collection is fuzzier and contains more information for judg-ment. ... pages 89–92,Prague, June 2007.c2007 Association for Computational LinguisticsTest Collection Selection and Gold Standard Generation for a Multiply-Annotated Opinion Corpus Lun-Wei Ku,...
... ‘‘%’’ for abandoned sentences and ‘‘x’’ for noise.CallHome Spanish is further annotated for dialogue games and activities. Dialogue game annotation isbased on the MapTask notion of a dialogue ... 7: Information gain for FLSAis also a high performance improvement. Occasion-ally, if the IG is small this does not hold. For exam-ple, using the previous DA reduces the entropy by0.21 for ... to dialogue act classi-fication. Dialogue systems need to perform dia-logue act classification, in order to understand therole the user’s utterance plays in the dialogue (e.g.,a question for...
... July 2006.c2006 Association for Computational LinguisticsA Flexible Approach to Natural Language Generationfor Disabled Children Pradipta Biswas School of Information Technology Indian ... Chinese. The NLG part of this system uses trigram language model for selecting appropriate inflectional form for target language generation. When NLG (or NLP) technology is ap-plied in assistive ... Rank(Pi)=Minimum(Counter(Tj)) for all j in Pi Now before sentence realization the phrases are ordered according to their rank. Each of these phrase orders produces a separate sentence. As for example let...
... the back-end, the Dialogue Manager can re-consult SR for other hypotheses. Alterna- tively, the Dialogue Manager can fire Natural Language Generation with an output request for clarification. ... example dialogues have more primitive cousins under development today. Briefly, our example dialogue types are listed in Table 3. Dialogue with an Appliance Dialogue with an Application Dialogue ... 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 either user...
... 2007.c2007 Association for Computational LinguisticsCombining Multiple Knowledge Sources forDialogue Segmentation inMultimedia ArchivesPei-Yun HsuehSchool of InformaticsUniversity of EdinburghEdinburgh, ... interpretation does not holdtrue for all tasks.3 For example, Gruenstein et al.(2005) report kappa(PK/WD) of 0.41(0.28/0.34) for determining the top-level and0.45(0.27/0.35) for the sub-level segments ... dialogue acttype4and speaker role (e.g., project manager, mar-4In the annotations, each dialogue act is classified as oneof 15 types, including acts about information exchange (e.g.,Inform),...
... tuples for train-ing, 240 tuples for development and 240 for test-ing). Documents and captions were parsed withthe Stanford parser (Klein and Manning, 2003) inorder to obtain dependencies for ... infor-mation in a story.7This is an encouraging resultas it highlights the importance of the visual infor-mation for the caption generation task. In general,word overlap is the worst performing ... phrase-based model for both image annota-tion and caption generation. We also believe thatour approach would benefit from more detailedlinguistic and non-linguistic information. For in-stance,...