Báo cáo khoa học: "Learning Common Grammar from Multilingual Corpus" potx

... syntaxacross languages, and try to extract a common grammar from non-parallel multilingual corpora.For this purpose, we propose a generative modelfor multilingual grammars that is learned in anunsupervised ... corpora,where each sentence is generated from alanguage dependent probabilistic context-free grammar (PCFG), and these PCFGsare generated from a prior grammar thatis common across languages. We also ... 184–188,Uppsala, Sweden, 11-16 July 2010.c2010 Association for Computational LinguisticsLearning Common Grammar from Multilingual CorpusTomoharu Iwata Daichi MochihashiNTT Communication Science Laboratories2-4...

Báo cáo khoa học: "Learning Semantic Links from a Corpus of Parallel Temporal and Causal Relations" doc

... null label is NO-REL.train/test split from Table 1 and the feature sets:Syntactic The syntactic features from Section 4.Semantic The semantic features from Section 4.All Both syntactic and ... took, take, VBDand began, to, trade, begin, trade, VBD,TO,VB.• The syntactic paths from the ﬁrst event tothe common ancestor to the second event, e.g.VBD>VP, VP and VP<VBD.1Train: wsj ... prior work (Girju, 2003; Girju et al.,2007). Annotators selected the best paraphrase of“and” from the following options:CAUSAL and as a result, and as a consequence,and enabled by thatNO-REL...

Tài liệu Báo cáo khoa học: "Learning Event Durations from Event Descriptions" docx

... instances), from the TimeBank corpus annotated in TimeML (Pustejovky et al., 2003). The non-WSJ articles (mainly political and disaster news) include both print and broadcast news that are from ... two peaks in this distribution. One is from 5 to 7 in the natural logarithmic scale, which corresponds to about 1.5 minutes to 30 minutes. The other is from 14 to 17 in the natural logarithmic ... potentially very important in applications in which the time course of events is to be extracted from news. For example, whether two events overlap or are in sequence often de-pends very much...

Báo cáo khoa học: "Learning Semantic Categories from Clickthrough Logs" pdf

... both precision and recall.We cast semantic category acquisition from search logs as the task of learning labeled in-stances from few labeled seeds. To our knowledgethis is the ﬁrst study that ... different from ours. An-other line of new research is to combine various re-sources such as web documents with search querylogs (Pas¸ca and Durme, 2008; Talukdar et al.,2008). We differ from this ... pages 189–192,Suntec, Singapore, 4 August 2009.c2009 ACL and AFNLPLearning Semantic Categories from Clickthrough LogsMamoru KomachiNara Institute of Science and Technology (NAIST)8916-5 Takayama,...

Báo cáo khoa học: "Learning Constraint Grammar-style disambiguation rules using Inductive Logic Programming" potx

... of the Constraint Grammar (CG) (Karlsson et al., 1995) approach to part of speech tagging and surface syntactic depen- dency parsing is due to the minutely hand- crafted grammar and two-level ... Progol machine learning system will be presented very briefly. 1.1 Constraint Grammar POS tagging Constraint Grammar is a system for part of speech tagging and (shallow) syntactic depen- dency ... ported here is sampled from a pre-release of the Stockholm-Ume£ Corpus (SUC). SUC cov- ers just over one million words of part of speech tagged Swedish text, sampled from different text genres...

Báo cáo khoa học: "Learning Bilingual Lexicons from Monolingual Corpora" pot

... improvement over the 92.3 us-ing only the Wiktionary lexicon. Of the true errors,the most common arose from semantically relatedwords which had strong context feature correlations(see table ... aria42,pliang,tberg,klein }@cs.berkeley.eduAbstractWe present a method for learning bilingualtranslation lexicons from monolingual cor-pora. Word types in each language are charac-terized by purely monolingual ... matchings. We show thathigh-precision lexicons can be learned in a va-riety of language pairs and from a range ofcorpus types.1 IntroductionCurrent statistical machine translation systems useparallel...

Báo cáo khoa học: "Learning Transliteration Lexicons from the Web" pptx

... from corpora. The EX approach aims to construct a large and up-to-date transliteration lexicon from live corpora. Towards this objective, some have proposed extracting translation pairs from ... extraction of transliteration pairs (EX) from corpora. The TM approach models phoneme-based or grapheme-based mapping rules using a generative model that is trained from a large bilingual lexicon, ... observe common guidelines. They often skew the transliterations in different ways to create special meanings to the sound equivalents, resulting in casual transliterations. In this case, the common...

Báo cáo khoa học: "Learning Tense Translation from Bilingual Corpora" docx

... called me up. The following two grammar fragments describe the relevant CVP syntax for English and Ger- man. Every auxiliary verb governs only one verb, so the CVP grammar is basically 2 regu- ... Fortunately, the task can be (partly) automated if the tables associating words with biases are learned from a corpus. Statistical approaches also support empirical evaluation of different disambiguation ... (analytic tenses). 2 Words Are Not Enough Often, sentence meaning is not compositional but arises from combinations of words (1). (1) a. Ich habe ihn gestern gesehen. I have him yesterday seen...

Báo cáo khoa học: "Acquiring a Lexicon from Unsegmented Speech" potx

... a word grammar could be learned in conjunction with this acquisition process, and used as a disambiguation step. 3 Tests and Results To test the algorithm, we used 34438 utterances from the ... cgdemarc@ai.mit.edu Abstract We present work-in-progress on the machine acquisition of a lexicon from sen- tences that are each an unsegmented phone sequence paired with a primitive represen- ... recognition. 1 Introduction We are interested in how a lexicon of discrete words can be acquired from continuous speech, a prob- lem fundamental both to child language acquisition and to the...

Báo cáo khoa học: "Learning Semantic Correspondences with Less Supervision" potx

... mapping which doesnot arise from string operations but must insteadbe learned.We used the dataset created by Chen andMooney (2008), which contains 1919 scenarios from the 2001–2004 Robocup ... 3,753cities in the US (those with population at least10,000) over three days (February 7–9, 2009) from www.weather.gov. For each city and date, wecreated two scenarios, one for the day forecast ... timeintervals. For example, one of the records statesthe minimum, average, and maximum tempera-ture from 5pm to 6am. This aggregation pro-cess produced 22,146 scenarios, each containing|s| = 36...

Xem thêm