Báo cáo khoa học: "Discourse Structures for Text Generation" doc

... in a text. The pattern of instantiation of schemas in a text is called a text structure. So, for our example text, one part of its text structure says that the text span of the whole text ... more comprehensive and more informative about text function than the text organization parts of previous text generation systems. 1, The Text Organization Problem Text generation is already ... the Request schema for inducing actions, the Evidence schema for making claims credible, the/nform schema for causing the reader to know particular information, and so forth. Our knowledge...

Tài liệu Báo cáo khoa học: "Different Structures for Evaluating Answers to Complex Questions: Pyramids Won’t Topple, and Neither Will Human Assessors" docx

... Association for Computational LinguisticsDifferent Structures for Evaluating Answers to Complex Questions:Pyramids Won’t Topple, and Neither Will Human AssessorsHoa Trang DangInformation Access ... answering (QA) systems for addressing complex information needs has ne-cessitated the development and reﬁnement of newmethodologies for evaluating and comparing sys-tems. In the Text REtrieval Conference ... etc.). Typically, theseinformation needs are embedded in the context of ascenario (i.e., user task) and often require systems to768synthesize information from multiple documents orto generate...

Báo cáo khoa học: "Discourse Cues for Broadcast News Segmentation" potx

... Figure 1) or MS-NBC. For example, the structure for the Jim Lehrer News Hour provides not only segmentation information but also content information for each segment. Thus, the order of stories ... content-based information browsing, retrieval, extraction, and summarization to ensure their value for tasks such as real-time profiling and retrospective search. Whereas image processing for video ... discourse cue story segmentor has been implemented in the context of a multimedia (closed captioned text, audio, video) analysis system for web based broadcast news navigation. We employ a finite...

Tài liệu Báo cáo khoa học: "A Framework for Syntactic Translation" docx

... guistic structures, their equivalences, and meanings. The Problems The difficulties associated with word -for- word translation were appreciated from the very beginning, at least in outline form. ... solved by the proper manipulation or utilization of the context. Context is to be understood here in its broadest interpretation. Contextual clues were treated in detail in an earlier article.4 ... a suggestion by Bar- Hillel,5 do consider larger context, but by a complicated scanning forth and back in the sen- tence, looking for particular words or particular diacritics that have...

Tài liệu Báo cáo khoa học: "Gestural Cohesion for Topic Segmentation" docx

... gestures, in which theform of motion is the principle communicative fea-ture (McNeill, 1992).Non-textual features for topic segmentation Re-search on non-textual features for topic segmenta-tion ... unlike formal sign language – rarely fol-lows any predeﬁned form or grammar, and may varydramatically by speaker.A key implementational challenge is automati-cally extracting gestural information ... used for a variety of problems incomputer vision (Forsyth and Ponce, 2003), and pro-vide a fairly general way to describe the visual ap-pearance of small image patches. However, even for a...

Tài liệu Báo cáo khoa học: "Self-Training for Biomedical Parsing" doc

... June 2008.c2008 Association for Computational LinguisticsSelf-Training for Biomedical ParsingDavid McClosky and Eugene CharniakBrown Laboratory for Linguistic Information Processing (BLLIP)Brown ... al.,2006a; McClosky et al., 2006b).One possible use for this technique is for parser adaptation — initially training the parseron one type of data for which hand-labeled treesare available (e.g., ... results on self-training for pars-ing were n egative (Steedman et al., 2003; Char-niak, 1997). However more recent results haveshown that it can indeed improve parser perfor-mance (Bacchiani...

Tài liệu Báo cáo khoa học: "Discourse Obligations in Dialogue Processing" docx

... to perform the intended action, but a well-behaved agent might need to delay performance until the obligation is dealt with. For example, if the intention is to perform a series of inform acts, ... Some obligation rules based on the performance of con- versation acts are summarized in Table 1. When an agent performs a promise to perform an action, or performs an acceptance of a suggestion ... before considering other parts of the discourse context. Most obligations will result in the formation of intentions to communicate something back to the user. When the intentions are formed,...

Báo cáo khoa học: "A Procedure for Morphological Encoding" doc

... are required for the word forms of a given language. A part of such a ma- chine is shown in Figure 1. The sequences which this will generate are those required for the Future forms both of ... syntactic and semantic justification. The various forms discussed in this paper are customarily displayed in paradigms; for example, see Reynolds [1962] for the paradigms of MANDARE, a verb of the ... categories.1 For example, the Italian verb form canterá (possible translation: “he will sing”) may be identified, on the one hand, by a vocabulary element which we symbolize in the form CANTARE...

Báo cáo khoa học: "Interactive Visualization for Computational Linguistics" doc

...

Báo cáo khoa học: "Ensemble Methods for Unsupervised WSD" doc

... Association for Computational LinguisticsEnsemble Methods for Unsupervised WSDSamuel BrodySchool of InformaticsUniversity of Edinburghs.brody@sms.ed.ac.ukRoberto NavigliDipartimento di InformaticaUniversit`a ... sequences of re-lated words spanning a topical text unit (Mor-ris and Hirst, 1991). Algorithms for computinglexical chains often perform WSD before infer-ring which words are semantically related. ... sense of its context) in the lexicalknowledge base. The set of valid interconnectionsis determined by a manually-created context-freeMethod WSD Context RelationsLexChains types document ﬁrst-orderOverlap...

Xem thêm