Báo cáo khoa học: "Towards a model of formal and informal address in English" pdf

... Association for Computational LinguisticsTowards a model of formal and informal address in EnglishManaal FaruquiComputer Science and EngineeringIndian Institute of TechnologyKharagpur, Indiamanaalfar@gmail.comSebastian ... Bentivogli and Pianta, 2005).The phenomenon of formal and informal ad-dress has been considered in the contexts of transla-tion into (Hobbs and Kameyama, 1990; Kanayama,2003) and generation in Japanese ... across paralleltexts. Journal of Natural Language Engineering,11(3):311–325.Hiroshi Kanayama. 2003. Paraphrasing rules for au-tomatic evaluation of translation into Japanese. In Proceedings of...

Báo cáo khoa học: "Towards a Model of Face-to-Face Grounding" pptx

... empirical study and, based on our analysis of conversational data, propose a model of grounding using both verbal and nonverbal information, and present our im-plementation of that model into an ... Conversation can be seen as a collaborative activ-ity to accomplish information-sharing and to pur-sue joint goals and tasks. Under this view, agreeing on what has been said, and what is meant, ... 16 combinations of the nonverbal behaviors are defined, as shown in Table 1. Thus, gP/gM stands for a combination of speaker gaze at partner and listener gaze at map. Results We examine differences...

Tài liệu Báo cáo khoa học: "TOWARDS A THEORY OF COMPREHENSION OF DECLARATIVE CONTEXTS " docx

... on a data card for each student. The regis- trar also supplies data cards containing a student name, identification number and number of courses passed. The parser is invoked by activating ... languages as FRL, KLONE and KIIL. Frames have played dual functions. They have been used as a way to organize the inferences, and also as a structural representation of what is re- membered of a ... system of rules and concepts as an abstract representation (an epistemic notion that is absent in Schank and his collobarators' work). The in- clusion of this distinction in our model makes...

Báo cáo khoa học: "METONYMY: REASSESSMENT, SURVEY OF ACCEPTABILITY, AND ITS TREATMENT IN A MACHINE TRANSLATION SYSTEM S" ppt

... METONYMY: REASSESSMENT, SURVEY OF ACCEPTABILITY, AND ITS TREATMENT IN A MACHINE TRANSLATION SYSTEM Shin-ichiro Kamei* & Takahiro Wakao Computing Research Laboratory New Mexico State University ... article we outline a basic approach to treating metonymy properly in a multil- ingual machine translation system. This is the first attempt at treating metonymy in an machine translation environment. ... that the main factors for treating metonymy correctly in a multil- ingual machine translation system are 1) its universality, which can be a guideline for the analysis component, 2) language...

Tài liệu Báo cáo khoa học: Direct identiﬁcation of hydrophobins and their processing in Trichoderma using intact-cell MALDI-TOF MS docx

... anHFB1-like protein, which, after N-terminal processing(MKFFTAAALFAAVAIA), C-terminal processing(AVGA) and disulﬁde bond formation, has a mass of 7743 Da.T. longibrachiatumThe main mass peak of T. longibrachiatum ... the range of 5–10 kDa, typically including two dominating peaksat approximately m ⁄ z 7000. As mycelia and sporeslargely remained intact, and the extraction solutioncontained acetonitrile and ... than six small proteins; (b)known cleavage sites of signal peptidases and fungalKex2-like proteinases; and (c) actual structural studies of H. jecorina HFB1 and HFB2. In H. jecorina, maturation...

Tài liệu Báo cáo khoa học: "Towards a Computational Treatment of Superlatives" pptx

... found in natural language, with the exception of recent work by Bos and Nissim (2006) and Jindal and Liu (2006), they have not yet been investigated within a computational framework. And within ... product range. [21] In China, VW is by far [the largest car maker]. The phrases of cars and car in [18] and [19] both have the role of specifying the type of maker that constitutes the comparison ... use in applications such as Question Answering (QA) and Sentiment Detection and Opinion Extraction. That a computational treat-ment of superlatives is a worthwhile undertaking is also supported...

Báo cáo khoa học: "Towards a Semantic Classiﬁcation of Spanish Verbs Based on Subcategorisation Information" doc

... the overallquality of the clusters created. The main difficulty in evaluating unsupervised classification tasks against a gold standard lies in the fact that the class labels of the obtained clusters ... in nitival sentential clauses, and in nitivalsentential clauses introduced by a preposition. Theindividual prepositions are also taken into accountas part of the subcategorisation frame types.Adapting ... can observe thatthe best classification tasks in terms of the Silhou-ette measure are the 3-way and 15-way classifica-tions. The baseline is calculated, for each task, asthe average value of...

Báo cáo khoa học: "TOWARDS A NEW TYPE OF ANALYSE " pptx

... called TIBAQ (Text -and- Inference Based Answering of Questions, cf. (Haji~ov@ and Sgall, 1981)) with no pre-arranged data base and with the capacity of self- -enriching by information drawn ... above), tense (present, past and future), mood (indicative and imperative), and voice (active and passive). As concerns notation, usually several kinds of information are collapsed in a ... section 3, or that of t-~ word-inflection ending~ among masculine-inanimate, masculine-animate and feminine nouns with additional morphemically irresolvable ambiguity concerning case and number:...

Báo cáo khoa học: "Towards A Modular Data Model For Multi-Layer Annotated Corpora" docx

... developed in the project treat anno-tation data in XML from any source as separateannotation layers, provided the text nodes in eachlayer contain the same base data. The base data isextracted and ... data for any data we wantto annotate. A single instance of base data iscalled signal. Signals can be of many differentkinds such as images (e.g. scans of facsimiles) orstreams of text, audio ... annotated text corpora.While the XML standard speciﬁes a data model and serialization format for XML, a semanticsis largely left to be deﬁned for a particular ap-plication. Many data models can...

Báo cáo khoa học: "Towards a Cognitively Plausible Model for Quantification" docx

... Ottawa, Ontario, KIS-5B6 CANADA walid@eagle.hr.att.com Abstract The purpose of this paper is to suggest that quantifiers in natural languages do not have a fixed truth functional meaning as ... context, as well as time and memory constraints 1. 1 Introduction Virtually all computational models of quantification are based one some variation of the theory of generalized quantifiers (Barwise ... context-sensitive aspects of natural language by devising interpretation relative to a context, where the context was taken to be an "index" denoting a possible- world and a point in time. In this...

Xem thêm