Báo cáo khoa học: "THE SPECIFICATION OF TIME MEANING FOR MACHINE TRANSLATION" pot
... principles for the representation of time meanings: (I) Each time meaning representation contains exactly three time intervals: - the time of speech or narration (S) - the time of event (E), ... syntactic/morphological forms and time meanings, resulting in a non-arbitrary relation between form and meaning. Third, we show how the calculus can be used for the...
Ngày tải lên: 24/03/2014, 05:21
... Conference of the Associa- tion for Computational Linguistics. John DeNero and Dan Klein. 2008. The complexity of phrase alignment problems. In Proceedings of the Annual Conference of the Association for ... Ward, and Wei- Jing Zhu. 2002. BLEU: A method for automatic evaluation of machine translation. In Proceedings of the Annual Conference of the Association for Com-...
Ngày tải lên: 07/03/2014, 22:20
... the number of common words in the hypothesis and the reference (accounting for recall) and the num- ber of words of the hypothesis that do not appear in the reference (accounting for precision). As ... account. Let us introduce, for each word w, a variable γ w that denotes the number of times w appears in the hypothesis clipped to the number of times, it ap- pears in the refer...
Ngày tải lên: 24/03/2014, 03:20
Báo cáo khoa học: "Pattern-Based Context-Free Grammars for Machine Translation" pot
... explosive growth of the World-Wide Web (WWW) as information source, it has become rou- tine for Internet users to access textual data written in foreign languages. In Japan, for example, a dozen ... implementation of MT systems based on these formalisms, on the other hand, would not be possible without much more efficient parsing and disambiguation algorithms for these formali...
Ngày tải lên: 31/03/2014, 06:20
Báo cáo khoa học: "THE REPRESENTATION OF CONSTITUENT STRUCTURES FOR FINITE-STATE PARSING" pdf
... REPRESENTATION OF CONSTITUENT STRUCTURES FOR FINITE-STATE PARSING D. Terence Langendoen Yedldyah Langsam Departments of English and Computer & Information Science Brooklyn College of the City ... City University of New York Brooklyn, New York 11210 U.S.A. ABSTBACT A mixed prefix-postfix notation for repre- sentations of the constituent structures of the expressio...
Ngày tải lên: 08/03/2014, 18:20
Báo cáo khoa học: " The Development of Lexical Resources for Information Extraction from Text Combining Word Net and Dewey Decimal Classification" potx
... is one of the main bot- tlenecks in the development of new ap- plications in the field of Information Ex- traction from text. Generic resources (e.g., lexical databases) are promising for reducing ... others) most of the terms necessary for an IE application. Nevertheless up to now the use of generic resources within IE system has been limited for two main reasons. Firs...
Ngày tải lên: 08/03/2014, 21:20
Báo cáo khoa học: "The Semantics of Collocational Patterns for Reporting" pdf
... hinted at in MWDP, is an important part of the meaning of insisl. In a careful analysis of a 250,000 word text base of TIME magazine articles from 1963 (TIMEcorpus) [Berglerg0a] we confirmed ... preference for one particular metonymy, which is of special inter- est for reporting verbs, namely where the name of a country, of a country's citizens, of a capital,...
Ngày tải lên: 24/03/2014, 05:21
Báo cáo khoa học: The reconstitution of mammalian prion infectivity de novo pot
... PrP*, an intermediate form of the prion protein formed on the pathway toward PrP Sc ; PrP C , normal cellular isoform of the prion protein; PrP Sc , disease-associated isoform of the prion protein; ... affect the conforma- tional preferences of the PrP molecule for acquiring the fibrillar form of a specific conformation in vitro.Asa result, the subset of abnormal b-sheet-rich conf...
Ngày tải lên: 30/03/2014, 09:20
Báo cáo khoa học: "Unsupervised Learning of Dependency Structure for Language Modeling" potx
... Learning of Dependency Structure for Language Modeling Jianfeng Gao Microsoft Research, Asia 49 Zhichun Road, Haidian District Beijing 100080 China jfgao@microsoft.com Hisami Suzuki Microsoft ... the N-best list of N=100, whose “oracle” CER (i.e., the CER of the hy- potheses with the minimum number of errors) is presented in Table 1, indicating the upper bound on performanc...
Ngày tải lên: 17/03/2014, 06:20
Báo cáo khoa học: "A Class of Submodular Functions for Document Summarization" pot
... summaries of at most 250 words for each cluster. For each cluster, a title and a narrative describing a user’s information need are provided. The narrative is usually composed of a set of questions ... value of information in graphical models. In Proc. of Uncertainty in AI. A. Krause, H.B. McMahan, C. Guestrin, and A. Gupta. 2008. Robust submodular observation selection. Jour- n...
Ngày tải lên: 23/03/2014, 16:20