Báo cáo khoa học: " Translating Named Entities Using Monolingual and Bilingual Resources" ppt

... for translating named entity phrases using easily obtain-able monolingual and bilingual resources.We report on the application and evalua-tion of this algorithm in translatingArabic named entities ... Translating Named Entities Using Monolingual and Bilingual ResourcesYaser Al-Onaizan and Kevin KnightInformation Sciences InstituteUniversity ... phrases, and monetary expressions. While the identiﬁca-tion of named entities in text has received sig-niﬁcant attention (e.g., Mikheev et al. (1999) and Bikel et al. (1999)), translation of named entities has...

Tài liệu Báo cáo khoa học: "Question Answering by Lexical Fabric and External Resources" ppt

... things: entities and events. From their definitions inWordNet, an entity is anything having existence(living or nonliving) and an event is somethingthat happens at a given place and time. ... uses the knowledge of both theWeb and WordNet to expand the original query.This is done by first using the original query tosearch the web for top N,„ documents and extract-ing additional web ... tomaximize the answer recall and precision (Yang& Chua 2003). NLP analysis is performed onthese candidate sentences to extract part-of-speech tags, base Noun Phrases, Named Entities, etc.Finally,...

Báo cáo khoa học: "Recognizing Named Entities in Tweets" docx

... understanding, and customizing complex rule-based named- entityannotators for different domains.Ratinov and Roth (2009) systematically studythe challenges in NER, compare several solutions and ... dropnon-English tweets and get about 11,371,389, fromwhich 15,800 tweets are randomly sampled, and arethen labeled by two independent annotators, so thatthe beginning and the end of each named entity ... tweets, forming the gold-standard data set.Figure 1 shows the portion of named entities of dif-ferent types. On average, a named entity has 1.2words. The gold-standard data set is evenly split...

Báo cáo khoa học: "Contextualizing Semantic Representations Using Syntactically Enriched Vector Models" ppt

... the sum, orcentroid of a and b (Landauer and Dumais, 1997).Kintsch (2001) considers a variant of this simplemodel. By using vector representations of a predi-catep and an argumenta, Kintsch ... identifying paraphrase candidates and ranking them according to the context. We followE&P and evaluate it only on the second subtask:we extract paraphrase candidates from the goldstandard by pooling ... the model is in the goldstandard or not,Ris the size of the gold standard, and nis the number of paraphrase candidates tobe ranked. If we takexito be the gold standardweight of theith...

Báo cáo khoa học: "Sub-sentential Alignment Using Substring Co-Occurrence Counts" ppt

... substrings and 875 mil-lions unique French (word-) substrings. And things get much worse if we want to try to work with characters substrings. To handle this problem, we decided not to try and ... cases and will be neglected). We can now compute pf and pl for a substring S such as previously, and retrieve the sentence indexes corresponding to every suffix between positions pf and pl ... S1 and S2 in a parallel corpus. We compute beforehand the two Suffix Arrays for the 2 sides of the parallel corpus. We can then compute two occurrence vectors V1 and V2 for S1 and...

Báo cáo khoa học: "Exploiting Named Entity Taggers in a Second Language" ppt

... determiningboundaries of named entities, we called this process Named Entity Delimitation (NED). Once we havedetermined which words belong to named entities, we then get to the task of classifying the named en-tities ... different kindsof named entities: core NEs, which contain a trig-ger word as nucleus, syntactically simple weakNEs, formed by single noun phrases, and syntacti-cally complex named entities, comprised ... electronicform for only a handful of languages. We believethat, by using machine learning techniques, we canadapt an existing hand coded system to different do-mains and languages with little...

Báo cáo khoa học: "Parsing the WSJ using CCG and Log-Linear Models" pptx

... L-BFGS algorithm (Nocedal and Wright,1999). And ﬁnally, we show that the parsing algo-rithm described in Clark and Curran (2003) is ex-tremely slow in some cases, and suggest an efﬁcientalternative ... for estimation, and resulting in anextremely efﬁcient parser.This paper assumes a basic understanding ofCCG; see Steedman (2000) for an introduction, and Clark et al. (2002) and Hockenmaier ... conditional random ﬁelds, e.g. Sha and Pereira (2003). As an alternative to GIS, we haveimplemented a parallel version of our L-BFGS code using the Message Passing Interface (MPI) standard.L-BFGS...

Báo cáo khoa học: "Classifying French Verbs Using French and English Lexical Resources" pdf

... several super-vised and unsupervised evaluation metrics and (iii) of various existing syntactic and semanticlexical resources. We evaluate our approachon an established test set and show that itoutperforms ... (Sun et al., 2010) and to a lesser extent for German (Brew and Schulteim Walde, 2002; Schulte im Walde, 2003; Schulteim Walde, 2006), Japanese (Oishi and Matsumoto,1997) and Italian (Merlo ... (http://www.google.com/dictionary) and Dicovalence (van den Eynde and Mertens, 2003).3The training data consists of the verbs and Verbnet classesused in the gold standard presented in (Sun et al.,...

Báo cáo khoa học: "Collocation Translation Acquisition Using Monolingual Corpora" pdf

... estimated using Equation (4) and the translation probabilities estimated using EM algorithm, we can compute the best triple translation for a given Chinese triple using Equations (1) and (7). ... achieves good results in word translation selection. In addition, (Dagan and Itai, 1994) and (Li, 2002) propose using two monolingual corpora for word sense disambiguation. (Fung, 1998) uses an ... (Rapp, 1999) and (Koehn and Knight, 2002) extract new word translations from non-parallel corpus. (Cao and Li, 2002) acquire noun phrase translations by making use of web data. (Wu and Zhou,...

Báo cáo khoa học: " Automatic Verb Classification Using Distributions of Grammatical Features" ppt

... language generation and machine translation (Dorr, 1997), and document classifica- tion (Klavans and Kan, 1998). Manual classifica- tion of large numbers of verbs is a difficult and resource intensive ... means that the system randomly divides the data into ten parts, and runs ten times on a different 90%-training-data/t0%-test-data split, yielding an average accuracy and standard error. This ... transitive (la) becomes the object of the transi- tive (lb) (Brousseau and Ritter, 1991; Hale and Keyser, 1993; Levin and Rappaport Hovav, 1995). The sentences in (2) use an unaccusative verb,...

Xem thêm