Báo cáo khoa học: "Parsing and Generation as Datalog Queries" doc

... →(e→t)→(e→t)→t,N → e→t}). A rule that has A onthe left-hand side and B1, ,Bn as right-hand sidenonterminals has its left-hand side annotated with awell-formed λ-term M that has type σ(A) under thetype ... Meeting of the Association of Computational Linguistics, pages 176–183,Prague, Czech Republic, June 2007.c2007 Association for Computational LinguisticsParsing and Generation as Datalog QueriesMakoto ... Montague semantics for En-glish and such “linear” grammar formalisms as (multi-component) tree-adjoining grammars (both as string grammars and as tree grammars) and mul-tiple context-free grammars....

Báo cáo khoa học: "Parsing and Subcategorization Data" pot

... WSJ as training data and section 23 as test data (Collins, 1999). For spoken language, wedesignated section 2 and 3 of Switchboard as train-ing data and ﬁles of sw4004 to sw4135 of section 4 as ... the internal structure of dif-ferent types of clause, as shown in Table1.• Passive Structures: As noted above,Roland and Jurafsky (Roland and Juraf-sky, 1998) have noticed that written lan-guage ... verb disambigua-tion and classiﬁcation (Schulte im Walde, 2000;Merlo and Stevenson, 2001; Lapata and Brew,2004; Merlo et al., 2005) and SCCs for semanticrole labeling (Xue and Palmer, 2004; Punyakanoket...

Báo cáo khoa học: "PARSING AND FASY" pptx

... guarantee easy parsability, as enforced by the bounded context eortstraJllt, are at least as strong as those required for easy learnability. This means that if we have a language and associated ... Marcus parser defines a class of languages (and associated grammars) that are easily pa~able; Degree 2 theory, a class of languages (and asstx:iated grammars) that is easily learnable. To begin ... functional demands be recrtnciled? There is in fact no a priori reason to believe that the demands of learnability and parsability are necessarily compatible. After all. learuability has to do...

Báo cáo khoa học: "Natural Language Generation as Planning Under Uncertainty for Spoken Dialogue Systems" pptx

... al., 2008; Rieser and Lemon, 2008a) and “conversation as action under uncertainty”(Paek and Horvitz, 2000). In NLG we havesimilar trade-offs and unpredictability as in DM, and in some systems ... 16:105–133.Amanda Stent, Marilyn Walker, Steve Whittaker, and Preetam Maloor. 2002. User-tailored generation forspoken dialogue: an experiment. In In Proc. of IC-SLP.Amanda Stent, Rashmi Prasad, and ... Johnston, and G. Vasireddy. 2004.User tailored generation in the match multimodal di-alogue system. Cognitive Science, 28:811–840.Marilyn Walker, Amanda Stent, Franc¸ois Mairesse, and Rashmi Prasad....

Báo cáo khoa học: "Parsing and Subcategorization Data" ppt

Báo cáo khoa học: "PARSING AND DERIVATIONAL EQUIVALENCE" pptx

... we now assign scores as follows: (38) a. An elementary tree has score I b. If a left subtree has score z and a right subtree has score y, the binary-branching tree formed from them has score ... tree structure as follows: (28) a. An elementary tree has score 1 b. If a left subtree has score z and a right subtree has score y, the binary-branching tree formed from them has score 2z -t- ... distinct normal forms P and Q, then X PandY Q, butP~Q, soX~ Y. 2Suppose P and Q are distinct normal forms and that P Q. Because normal forms only reduce to themselves and P and Q are distinct,...

Báo cáo khoa học: "PARSING AND INTERPRETING COMPARATIVES" ppt

... less and as much as, used together with an adjective, adverb or determiner, we also include such words as same, before and after, used in appropriate ways. We also try to give a usable classification ... than Mary. 2) Few people run as fast as John. 3) John bought more books than Mary. 4) John was happier in New York than in London. 5) John has more books than Mary has newspapers. 6) John had ... possible to rewrite simple phrasal comparatives into directly interpreted phrasal comparatives, and also to rewrite directly interpreted phrasal comparatives as clausal comparatives. We think,...

Tài liệu Báo cáo khoa học: "WORD AND OBJECT IN DISEASE DESCRIPTIONS" doc

... ease, and would accordingly have a high 'entropy'. Tables 2 and 3 show the top and bottom of the list of all words occurring in two or more diseases sorted by this entropy measure. ... words and medical terms. We measured word frequency by "disease occur- rence", (the number of disease definitions in which a given word occurs one or more times). By this measure, ... entropy-like measure of the distribution of word occurrences over the eleven physiological categor- ies as a measure of category specificity. We reasoned that some medical terms such as 'murmur',...

Báo cáo khoa học: Structure and function of KH domains docx

... antiparallel b-strands is abutted bythree a-helices (a1, a2, and a¢). The b-sheet in type IKH domains consists of three b-strands in the orderb1, b¢ and b2. The b1-strand and b2-strand are parallelto ... up and across from theGXXG loop, as in type I KH domains. The 5¢-endof the RNA (bases A42 through A45) is buried in and across the groove between the a1-helix and a2-helix and the b2-strand ... the b1-strand and b2-strand are adjacent and parallel to each other, and the b¢-strand is adja-cent and antiparallel to the b1-strand (Fig. 1). Thelength and sequence of the variable loop are...

Báo cáo khoa học: "Fast and accurate query-based multi-document summarization" docx

... USAFirstName.LastName@Thomson.comAbstractWe present a fast query-based multi-documentsummarizer called FastSum based solely onword-frequency features of clusters, docu-ments and topics. Summary ... 205–208,Columbus, Ohio, USA, June 2008.c2008 Association for Computational LinguisticsFastSum:Fast and accurate query-based multi-document summarizationFrank Schilder and Ravikumar KondadadiResearch ... least three fuzzy matches withthe topic description.3Features are mainly based on word frequencies ofwords in the clusters, documents and topics. A clus-ter contains 25 documents and is associated...

Xem thêm