Báo cáo khoa học: "Using Generation for Grammar Analysis and Error Detection" pptx

... ﬂaw in the grammar, and with enough examples we can pin-point the grammar rules causing these problems.We call our system Egad, which stands for Erro-neous Generation Analysis and Detection.∗This ... not cover all cases.3 Grammar Analysis When analyzing a grammar, Egad looks at all in-put sentences, parses, and generations processedby the grammar and uses the information thereinto determine ... Papers, pages 109–112,Suntec, Singapore, 4 August 2009.c2009 ACL and AFNLPUsing Generation for Grammar Analysis and Error DetectionMichael Wayne Goodman∗University of WashingtonDept....

Báo cáo khoa học: "Using Deep Morphology to Improve Automatic Error Detection in Arabic Handwriting Recognition" pot

... punctua-tion and digit) and error types. INS, DEL and SUB stand for insertion, deletion and substitution error types, re-spectively. Ortho stands for orthographic variant. Lemmastands for ‘shared ... punctuation and 3.5% digits.Orthogonally, 81.4% of all problem words aresubstitution errors, 10.6% are insertion errors and 7.9% are deletion errors. Whereas punctuation sym-bols are 9.3% of all errors, ... word form used to representthe lexeme word set – a citation form that standsin for the class (Habash, 2010). For instance, thelemma  mktb ‘ofﬁce’ represents the class ofall forms...

Báo cáo khoa học: "Variational Inference for Grammar Induction with Prior Knowledge" pdf

... 1–4,Suntec, Singapore, 4 August 2009.c2009 ACL and AFNLPVariational Inference for Grammar Induction with Prior KnowledgeShay B. Cohen and Noah A. SmithLanguage Technologies InstituteSchool ... probabilistic grammar (Pereira and Schabes, 1992). Later approaches in-clude variational EM in a Bayesian setting (Beal and Gharamani, 2003), which has been shown toobtain even better results for various ... exploredin order to improve performance. For example,Smith and Eisner (2006) have penalized the ap-proximate posterior over dependency structuresin a natural language grammar induction task toavoid...

Báo cáo khoa học: "Using aggregation for selecting content when generating referring expressions" pdf

... following: 3 1. (A (small black and a large white) dog) and (a small black cat). 2. (A small black (dog and cat)) and (a large white dog). The former groups together ol and o2 on the basis of their ... ol and 03 have equal values for both their size and color attributes but not for their type attributes. The one-valued context readily supports the derivation of formal con- cepts. A formal ... re- spect to any other distracting value for arg2, and so g7 and g8, both collectively and individ- ually, are appropriate and sufficient RE's for tl. • Rendering these in English would...

Báo cáo khoa học: "Personality Generation for Dialogue" ppt

... quality, at-mosphere, and service and categorical attributes for neighborhood and type of cuisine. SPaRKy is basedon the standard NLG architecture (Reiter and Dale,2000), and consists of the ... cues for extraversion, based on Dewaele and Furnham (1999); Furnham(1990); Mehl et al. (2006); Oberlander and Gill (2006); Pennebaker and King (1999), as well as PERSON-AGE’s corresponding generation ... recommendations and comparisons in the restaurant domain, for adatabase of restaurants in New York City. Thereare eight attributes for each restaurant: the name and address, scalar attributes for price,...

Tài liệu Báo cáo khoa học: "AN ALGORITHM FOR IDENTIFYING COGNATES BETWEEN RELATED LANGUAGES" pptx

... algorithm is given no information whatsoever about the phonemic transcription .used, and even though cognate identification is carried out on the basis of a context-free one -for- one matching ... "n", "a", or "s", and so may Titia "a", "t", "s", and "s". We summarize the evidence for these possible correspondences in an ... between tbe Titla and Sese word pairs were random the expected frequency e[i,J] of recorded possible correspon- 448 dences between the ith character of the Tltla alphabet and the jth of the...

Tài liệu Báo cáo khoa học: "Generalization Methods for In-Domain and Cross-Domain Opinion Holder Extraction" pdf

... Linguistics (ACL), Sapporo, Japan.John Lafferty, Andrew McCallum, and FernandoPereira. 2001. Conditional Random Fields: Prob-abilistic Models for Segmenting and Labeling Se-quence Data. In Proceedings ... adhere tothe deﬁnition of opinion holders from previouswork (Wiegand and Klakow, 2010; Wiegand and Klakow, 2011a; Wiegand and Klakow, 2011b),i.e. every source of a private state or a subjectivespeech ... for chunk parsing CASS (Abney, 1991) and for con-stituency parsing Stanford Parser (Klein and Man-ning, 2003). Named-entity information is pro-vided by Stanford Tagger (Finkel et al., 2005).4.2...

Báo cáo khoa học: "A System for Semantic Analysis of Chemical Compound Names" pdf

... different names and name types for onechemical compound, namely several systematic,semi-systematic, trivial and trade names. For ex-ample, pentan-2-ol is the recommended name for the compound ... syntactic analysis of a given name and alsoprovides a semantic representation. This seman-tic representation can be used as a basis for fur-ther processing, namely for structure generation or ... set of ver-tices and its set of edges. Therefore, the domain ofa graph consists of a set of possible vertices, in ourcase for the atoms, and possible edges, in our case for the bonds. The...

Báo cáo khoa học: "A System for Detecting Subgroups in Online Discussions" pptx

... package.The system works on all the standard platforms.The system has a command-line interface that2http://nlp.stanford.edu/software/corenlp.shtml3http://java-ml.sourceforge.net/provides full access ... www.createdebate.com,www.forandagainst.com, etc(1) Discussant 1: I believe that school uniform is agood idea because it improves student attendance.(2) Discussant 2: I disagree with you. School uniformis ... sentiment analysis and online discussion mining.Many previous systems studied the problem of iden-133tifying the polarity of individual words (Hatzivas-siloglou and McKeown, 1997; Turney and Littman,2003)....

Báo cáo khoa học: "Using Focus to Generate Complex and Simple Sentences" pot

... the basis for McKeown's and Appelt's and emphasizes the development of a formalism and grammar for generation that allows for the use of functional information. Both McKeown and Appelt ... bought a book and a cassette. 9. Mary read the book and played the cassette. 4. A Formalism for Surface Generation In this section we discuss the Prolog definite clause grammar (DCG) formalism ... (Pereira and Warren, 1980) and how it can be used for language generation, as well as recognition. We then review the functional grammar formalism (Kay, 1979) that has been used in other generation...

Xem thêm