... found in a writ- ten text. extended in order to maintain a coherent discourse structure for the modelling of the producer. Thus rhetorical relations describing planning processes are introduced. ... remaining part of the paper is organised as follows. Section 2 contains a description of the ex- perimental setting in which the example discourse was obtained (Habel and Tappe, forthcoming). ... the discourse segment containing (U2) and (U3) is 'cut off' and not available for further attachment. Embedded within the expectation is an utterance describing the ongoing planning...
... discourse purpose/intention. Satisfying the main discourse purpose is achieved by satisfying several smaller purposes/intentions organized in a hierar-chical structure. As a result, the discourse ... result, the instruction did not match the initial essay quality. Nonetheless, in the open-question interviews, many users indicated using the NM as a reference while updating their essay. In addition ... analy-sis of discourse segments in direction-giving mono-logues. In Proc. of ACL. E. Hovy. 1993. Automated discourse generation using discourse structure relations. Articial Intelligence,...
... 941Proceedings of the COLING/ACL 2006 Main Conference Poster Sessions, pages 937–944,Sydney, July 2006.c2006 Association for Computational LinguisticsStochastic Discourse Modeling inSpoken ... accurate information obtained by the machine (Higashinaka et al., 2004), the more possibility to finish the dialogue task. Practical use of speech act theories inspoken lan-guage processing (Stolcke ... training corpus. From this figure, we can find that more training sentences for the se-mantic dependency graph with discourse analysis are needed than that without discourse. This im-plies discourse...
... Improving Coherence in Students' WritingChien-Ching Leeleecc [at] ntu.edu.sgNanyang Technological University (Singapore)Low English proficiency students have difficulty making their writing ... out in the diagram. Futhermore, the ideas could be easily toggled around and edited if in the process of writing, they discovered more interesting ideas to write about.Seeing is Understanding: ... writing (if they get stuck in their writing, they will just start all over again using another word in the topic that they can relate to and tell about). They also spend little time planning...
... information is added as default, but it may also originate in preceding units. Thus words are linked to each other into phrases, phrases into clauses,clauses into sentences, sentences into discourses, ... any utterance. Accentual emphasizing in thesesituations are causing by tempo to express the informed information in each intonationunit.• Discourse function: Intonation helps speakers and hearers ... range of possibilities that exist for linking something withwhat has gone before. Since this linking is achieved through relations in meaning (we areexcluding from consideration the effect of formal...
... devices in narrative discourse How prosodic means in general and intonation in particular become a cohesive device in narrative discourse. SCOPE OF THE STUDYSCOPE OF THE STUDYCohesion in narrative ... COHESIVE S DEVICES IN COHESIVE S DEVICES IN NARRATIVE DISCOURSE NARRATIVE DISCOURSE MA THESISPresenter: Nguyen Thu Phuong RATIONALE OF THE STUDYRATIONALE OF THE STUDYThe linguists has ... narrative discourse is a big area.The study only focus on the grammatical means and intonation as cohesive devices in the film “The Perfect Man” on HBO channel. CONTENTSCONTENTS•Introduction•Literature...
... meeting recording andplayback system, and the benefit of topic-level anno-tations to meeting browsing. In Proceedings of the10th International Conference on Human-ComputerInteraction.Regina ... drawn in Section 5.2 Background and Related Work In this paper we are interested inspoken discourse, and in particular multi-party human-human meet-ings. Our overall aim is to produce informationwhich ... Usingsimple speech-based features to detect the state of ameeting and the roles of the meeting participants. In Proceedings of the 8th International Conference on Spoken Language Processing.Satanjeev...
... althoughunderstandable in the context of informing work on spoken dialogue systems, is somewhat at odds with previous think-ing about turn-taking. Although turn-taking behaviour is cul-turally ... below 400ms, and increasing the thresh-old value in increments of 100ms.Table 2 shows the values for the highest perform-ing models. The model that only inserts continuers in pauses over 900 ... CHIConference on Human Factors in Computing Systems.V.H. Yngve. 1970. On getting a word in edgewise. In Pa-pers from the Sixth Regional Meeting, Chicago LinguisticSociety, pages 567-577.58...
... Identifyingnon-referential it: a machine learning approach incor-porating linguistically motivated patterns. In Proceed-ings of the ACL Workshop on Feature Selection for Ma-chine Learning in NLP, Ann Arbor, ... Satou (2004). Improv-ing the identification of non-anaphoric it using SupportVector Machines. In International Joint Workshop onNatural Language Processing in Biomedicine and itsApplications, ... whichis frequent inspoken language, but rare in writtentext. It covers instances of it which are indeed ref-erential, but whose referent is not an identifiablelinguistic string in the context...
... user whoprefers flying business class, on direct flights, andon KLM, in that order. In FLIGHTS, coherence and naturalness of descriptions were increased byreasoning about information structure ... of interest for any rational user. All dominantoptions represent some tradeoff, but depending onthe user’s interest, some of them are more interest-ing tradeoffs than others.Pruning dominated ... forcooperative response generation in information dialogues. In AAAI/IAAI 1999 pp. 148–155.M. Steedman 2000. Information structure and the syntax-phonology interface. In Linguistic Inquiry, 31(4): 649–689.A....
... words inspoken and written corpus, in order to examine whether thereare any register variations.Chapter 7 will present the conclusions of this study.1. 4 Main FindingsThe main findings of ... gnarring sound.g. The wild not … of the bullfinch … is a most jarring and disagreeable noise.h. Through the plashing streets.i. Attended with pricking pains in the right side.j. The rapid increase ... but it marks nominalcrashas“following (i.e. being associated with) verbalcrash.” In a simple search of entriesincludingonomatop* in etymologies, only verbalcrashwas found. In this study,...
... kept inin the cage. Despite my seemingly never-ending agnostic questioning and doubting, in light of the evidence revealed in this book, it seems prudent to hedge my bets at this point and ... disconcerting to have madame knitting all the way there, in a public conveyance; it was additionally disconcerting yet, to have madame in the crowd in the afternoon, still with her knitting in her ... been doing these days?B: Ф Preparing for the driving license test A : Have you been swimming?B : yes, I have ФA : What have you been doingB : Ф swimming Those who prefer Ф, can stay indoors...
... paper we examine novel types of entrain-ment in two corpora—Switchboard and theColumbia Games corpus. We examine en-trainment in use of high-frequency words (themost common words in the corpus), ... had a highinclination for empathy (understanding the point ofview of the other) entrained to a greater extent thanothers. Reitter et al. (2007) also found that degree ofentrainment in lexical ... correlates with task success andminimal interruptions—important goals of SDS. In future work we will explore the consequences ofsystem entrainment to SDS users in helping systemsachieve these goals,...
... approach is novel in combining machine learning with n-best processingfor spoken dialogue systems using the InformationState Update approach.Our best results, obtained using TiMBL with op-timized ... importance of such tuning.Future work points in two directions: first, inte-grating our methodology into working ISU-baseddialogue systems and determining whether or notthey improve in terms of standard ... the remaining data into an80% training and 20% test set.3. Run TiMBL with all possible parameter set-tings on the generated training and test setsand store the best performing settings.4....
... computational model for generatingreferring expressions in a multilingual application do-main. In COLING–1996: Proceedings of the 16th In- ternational Conference on Computational Linguistics,Copenhagen, ... 247–62.Springer-Verlag,Berlin.Robert Dale. 1992. Generating Referring Expressions.MIT Press.Barbara Di Eugenio. 1998. Centering in Italian. In Marilyn A. Walker, Aravind K. Joshi, and Ellen F.Prince, ... during parsing, they ig-nore structures such as the discourse plan which arepresent during generation but not parsing. A typi-cal discourse plan can include vital information forpronominalization...