Báo cáo khoa học: "Multilingual WSD with Just a Few Lines of Code: the BabelNet API" pdf

... LinguisticsMultilingual WSD with Just a Few Lines of Code: the BabelNet APIRoberto Navigli and Simone Paolo PonzettoDipartimento di InformaticaSapienza Universit` a di Roma{navigli,ponzetto}@di.uniroma1.itAbstractIn ... Italian).3 An API for multilingual WSD BabelNet API. BabelNet can be effectively ac-cessed and automatically embedded within applica-tions by means of a programmatic access. In orderto achieve ... the lines of Navigli and Lapata (2010).At its core, the API leverages an in-house Java li-brary to query paths and create semantic graphs with BabelNet. The latter works by pre-computingoff-line...

Tài liệu Báo cáo khoa học: "What lies beneath: Semantic and syntactic analysis of manually reconstructed spontaneous speech" pdf

... Proceedings of the 47th Annual Meeting of the ACL and the 4th IJCNLP of the AFNLP, pages 746–754,Suntec, Singapore, 2-7 August 2009.c2009 ACL and AFNLPWhat lies beneath: Semantic and syntactic analysis of ... We analyzedsyntactic and semantic variation between originaland reconstructed utterances according to manu-ally and automatically generated parses and man-ually labeled semantic roles.Argument ... directly trans-late to them.2. Overlay tagged words of string Wvand Wr with the automatic (or manual) parse of the same string.3. Propagate labels. For each constituent in the parse, if all children...

Tài liệu Báo cáo khoa học: "Identifying Linguistic Structure in a Quantitative Analysis of Dialect Pronunciation" docx

... successful in the analysis of the dialect vari-ation, all of them aggregate over the entire availabledata, failing to extract linguistic structure from the aggregate analysis. Two attempts to ... toolkit was usedin order to make an aggregate analysis of Bulgariandialects. In this section more information on the dataset used in the project, as well as on the process of the aggregate analysis ... the distances obtained by the aggregate analysis. The square of the Pearson correlation coefﬁcient pre-sented in column 3 enables us to see that 39.0% and30.7% of the variance in the aggregate analysis...

Báo cáo khoa học: "Searching for Topics in a Large Collection of Texts" doc

... process of search-ing and consequently also the character of re-sulting concept-formative clusters. We have op-timized their values by a sort of machine learn-ing, using a small manually annotated ... ambiguity in the data,and its main advantage over hard clustering isthat it yields much more detailed informationon the structure of the data (cf. (Kaufman andRousseeuw, 1990), chapter 4).Then we ... wholecollection, and then each of them is used as a seedfor the Local Search algorithm, which locallyoptimizes the quality function .Note that are crucial parameters,which strongly affect the whole...

Tài liệu Báo cáo khoa học: Anaerobic sulfatase-maturating enzyme – A mechanistic link with glycyl radical-activating enzymes? docx

... TATTAT-3¢ and 5¢- ATA ATA GGC GTA TTC GGC TGCGAG GTT GGC TAC GGC-3¢; for the C27 6A ⁄ C28 2A mutant, 5¢-GGC GTA GCT ACA ATG GCG AAG CATGCC GGA CAT-3¢ and 5¢-ATG TCC GGC ATG CTTCGC CAT TGT AGC ... TAC GCC-3¢; and for the C33 9A ⁄ C34 2A ⁄ C34 8A mutant, 5¢- ACC CAA GCC AAGGAG GCC GAC TTT CTA TTT GCC GCC AAC GGA-3¢ and 5¢-TCC GTT GGC GGC AAA TAG AAA GTCGGC CTC CTT GGC TTG GGT-3¢ (the altered ... Benjdia A, Leprince J, Sandstrom C, Vaudry H &Berteau O (2009) Mechanistic investigations of anaero-bic sulfatase-maturating enzyme: direct Cbeta H-atomabstraction catalyzed by a radical AdoMet...

Tài liệu Báo cáo khoa học: Amprenavir complexes with HIV-1 protease and its drug-resistant mutants altering hydrophobic clusters docx

... close to the main chain of the cata-lytic aspartates forming new van der Waals contactsand a C-HÆÆÆO interaction. These new contacts with Asp25 ⁄ 25’ near the dimer interface correlate with the reduced ... National Insti-tutes of Health grant GM062920. We thank the staff atSER-CAT beamline at the Advanced Photon Source,Argonne National Laboratory, Argonne, IL, USA, forassistance during X-ray data ... Molecular Basis of Disease Program, Georgia State University, Atlanta, GA, USA2 Department of Computer Science, Molecular Basis of Disease Program, Georgia State Univers’ity, Atlanta, GA, USA3 Department...

Tài liệu Báo cáo khoa học: "Semantic Parsing with Bayesian Tree Transducers" doc

... prac-tice and submit each parse as a GeoQuery databasequery, and say the parse is correct only if the answermatches the gold standard. We report raw accuracy (the percentage of sentences with ... natural languageand meaning representation. However, whiletree transformations are central to severalstate -of- the- art approaches, little use has beenmade of the rich literature on tree automata.This ... rep-resented as trees, either by pre-parsing or becausethey are already trees (often the case for functionallanguages like LISP).1More speciﬁcally, we assume the MR language is a regular tree language.A...

Tài liệu Báo cáo khoa học: "Multilingual Pseudo-Relevance Feedback: Performance Study of Assisting Languages" doc

... (defendending), martina, jovotna, navratilovaGERMAN '01: TOPIC 91ESAI in LateinamerikaLa gripe aviar en América LatinaAI in Latin America0.4560.098international, amnesty, strassenkind ... by taking the help of a different language called the assisting language.In MultiPRF, given a query in source languageL1, the query is automatically translated into the assisting language ... assource languages and Dutch, English and Span-ish as the assisting language. We later vary the assisting language, for each source language andstudy the effects. We use the Terrier IR platform(Ounis...

Tài liệu Báo cáo khoa học: "Word Alignment with Synonym Regularization" doc

... proposedword alignment model on the additional trainingdata and the 347 sentence pairs of the evaluationdata. Note that manual word alignment of the 347 sentence pairs was not used for the unsuper-vised ... Akinori Fujino, and Masaaki NagataNTT Communication Science Laboratories, NTT Corp.2-4 Hikaridai Seika-cho Soraku-gun Kyoto 619-0237 Japan{shindo ,a. fujino}@cslab.kecl.ntt.co.jpnagata.masaaki@lab.ntt.co.jpAbstractWe ... sets decreased as a result of em-ploying the SRH.We show the performance of GIZA++ and HM-BiTAM with the SRH in the lines entitled with SRH” in Table 1. The GIZA++ and HM-BiTAM with the SRH...

Tài liệu Báo cáo khoa học: "Coreference Resolution with Reconcile" pdf

... available. JavaRap (Qiu et al.,2004) is an implementation of the Lappin andLeass’ (1994) Resolution of Anaphora Procedure(RAP). JavaRap resolves only pronouns and, thus,it is not directly comparable ... classification phase (i.e., assum-ing that a trained classifier is present). The basic architecture of the system includesfive major steps. Starting with a corpus of docu-ments together with a ... Inference with a Factored Model for Natural Language Parsing. In Ad-vances in Neural Information Processing (NIPS 2003).S. Lappin and H. Leass. 1994. An algorithm for pronom-inal anaphora resolution....

Xem thêm