... using statisticallanguage models. In this paper, we also use support vectormachines to combine features from tradi-tional reading level measures, statistical language models, and other language ... relative toeach other.4.1 StatisticalLanguageModels Statistical LMs predict the probability that a partic-ular word sequence will occur. The most commonlyused statisticallanguage model is the ... of syntax. Our approach uses n-gram languagemodels as a low-cost automatic ap-proximation of both syntactic and semantic analy-sis. Statisticallanguagemodels (LMs) are used suc-cessfully...
... decades of statistical language modeling: Where do we go from here? In Proceed-ings of IEEE:88(8).Rosenfeld R. 2000. Incorporating Linguistic Structureinto StatisticalLanguage Models. In ... comparison of in-grammar recognition performance.3 Language modellingTo generate the different trigram language models we used the SRI language modelling toolkit (Stol-cke, 2002) with Good-Turing ... movespecific statisticallanguagemodels (DM-SLMs)by using GF to generate all utterances that arespecific to certain dialogue moves from our in-terpretation grammar. In this way we can pro-duce models...
... of statistical machine translation: Parameter estimation. Computa-tional Linguistics, 19(2):263–311.Eugene Charniak, Kevin Knight, and Kenji Yamada.2003. Syntax-based languagemodels for statistical machine ... as language models for statistical machine translation. In Proceed-ings of AMTA.Sylvain Raybaud, Caroline Lavecchia, David Langlois,and Kamel Sma¨ıli. 2009. New confidence measuresfor statistical ... Computational LinguisticsEnhancing LanguageModels in Statistical Machine Translationwith Backward N-grams and Mutual Information TriggersDeyi Xiong, Min Zhang, Haizhou LiHuman Language TechnologyInstitute...
... research in statistical machine trans-lation has effectively used n-gram word sequence models as language models. Modern phrase-based translation using large scalen-gram languagemodels generally ... to incorporate large-scale n-gram languagemodels in conjunction withincremental syntactic language models. The added decoding time cost of our syntactic language model is very high. By increasing ... translation model. Instead, we incor-porate syntax into the language model.Traditional approaches to languagemodels inspeech recognition and statistical machine transla-tion focus on the use of...
... language models trained from text or speech corpora of vari-ous genres and sizes. The largest available language models are based on written text: we investigate theeffect of written text languagemodels ... dif-ferences among the different languagemodels whenextended features are present are relatively small.We assume that much of the information expressedin the languagemodels overlaps with the lexical ... information fromthe external languagemodels by defining a rerankerfeature for each external language model. The valueof this feature is the log probability assigned by the language model to the candidate...
... 2006. MAP adaptation of stochasticgrammars. Computer Speech & Language, 20(1):41 –68.Jerome R. Bellegarda. 2004. Statisticallanguage modeladaptation: review and perspectives. Speech Commu-nication, ... of EnglishBigrams. Computer Speech & Language, 5(1):19–54.Joshua Goodman. 2001. A Bit of Progress in Language Modeling. Computer Speech & Language, 15(4):403–434.Bo-June (Paul) Hsu ... N-gram LanguageModels Based onOrdinary Counts. In Proceedings of the ACL-IJCNLP2009 Conference Short Papers, pages 349–352.Ronald Rosenfeld. 1996. A Maximum Entropy Ap-proach to Adaptive Statistical...
... Kneser-Ney andthose methods.1 Introduction Statistical languagemodels are potentially usefulfor any language technology task that producesnatural -language text as a final (or intermediate)output. ... perplexity of any known methodfor estimating N-gram language models. Kneser-Ney smoothing, however, requiresnonstandard N-gram counts for the lower-order models used to smooth the highest-order model. ... best approach when language models based on ordinary counts are desired.ReferencesChen, Stanley F., and Joshua Goodman. 1998.An empirical study of smoothing techniques for language modeling....
... framework, real-time is re-quired.4 Phrase-based models The usual statistical translation models can beclassified as single-word based alignment models. Models of this kind assume that an input word ... framework (Och et al., 2003).Phrase-based models have proved to be very ad-equate statisticalmodels for MT (Tom´as et al.,2005). In this work, the use of these models hasbeen extended to interactive ... Therefore, thesame techniques (translation models, decoder al-gorithm, etc.) which have been developed forSMT can be used in CAT.Note that the statisticalmodels are defined atword level. However,...
... max-imum entropy models for statistical machine translation. InProc. of ACL, pages 295–302.F. J. Och and H. Ney. 2003. A systematic comparison of vari-ous statistical alignment models. Computational ... Constrained Word Alignment Models The framework that we propose to incorporate sta-tistical constraints into word alignment models isgeneric. It can be applied to complicated models such IBM Model-4 ... translation performance.1 Introduction Statistical word alignment models learn word as-sociations between parallel sentences from statis-tics. Most models are trained from corpora in anunsupervised...
... "Class-based n-gram models of natural language. " Computa- tional Linguistics, 18(4), pages 467-479. D. M. Magerman. 1994. Natural Language Pars- ing as Statistical Pattern Recognition. ... One of the important points of this work is that statistical models of natural language should not be restricted to simple, context-insensitive models. In a problem like parsing, where long-distance ... SPATTER's models SPATTER consists of three main decision-tree models: a part-of-speech tagging model, a node- extension model, and a node-labeling model. Each of these decision-tree models are...
... 2007. Large language models in machine translation. In Proceedingsof the 2007 Joint Conference on Empirical Meth-ods in Natural Language Processing and Com-putational Natural Language Learning ... Kneser-Ney smoothed n-gram models. IEEE Transac-tions on Audio, Speech and Language Processing,15(5):1617–1624.A. Stolcke. 1998. Entropy-based pruning of backoff language models. In Proc. DARPA ... wereselected for each language. The adaptation wasthought to take place off-line on a server.3.2.1 Data setsFor each language, the adaptation takes place ontwo baseline models, which are the...
... grammars for modeling agglutinationin this language, but first we will present the for-mer class of languages and its acceptor automata.3.1 Linear context free languages andtwo-taped nondeterministic ... 2010.c2010 Association for Computational LinguisticsThe use of formal languagemodels in the typology of the morphology ofAmerindian languagesAndr´es Osvaldo PortaUniversidad de Buenos Aireshugporta@yahoo.com.arAbstractThe ... natural representa-tion in terms of linear context-free languages.2 Quichua Santiague˜noThe quichua santiague˜no is a language of theQuechua language family. It is spoken in the San-tiago del...
... novel language modelcaching technique that improves the queryspeed of our languagemodels (and SRILM)by up to 300%.1 IntroductionFor modern statistical machine translation systems, language models ... with two different language models. Our first language model, WMT2010, was a 5-gram Kneser-Ney language model which storesprobability/back-off pairs as values. We trained this language model on ... and Smaller N -Gram Language Models Adam Pauls Dan KleinComputer Science DivisionUniversity of California, Berkeley{adpauls,klein}@cs.berkeley.eduAbstractN-gram languagemodels are a major...
... 2007.Compressing trigram languagemodels with golombcoding. In Proceedings of EMNLP-CoNLL 2007,Prague, Czech Republic, June.P. Clarkson and R. Rosenfeld. 1997 . Statistical language modeling using ... 2007a. Randomised language modelling for statistical machine translation. In 45thAnnual Meeting of the ACL 2007, Prague.D. Talbot and M. Osborne. 2007b. Smoothed Bloomfilter language models: Tera-scale ... alignmenttemplate approach to statistical machine translation.Computational Linguistics, 30(4):417–449.Andreas Stolcke. 1998. Entropy-based pruning of back-off language models. In Proc. DARPA Broadcast...
... linear models via a dynamic program. In the CMM, the local linear models are trained independently, while in the CRF model, the local models are trained jointly. We call these two linear models ... non-zero weight. 3.2 Language model adaptation Our experiments with LM adaptation are based on the work described in Gao et al. (2006). The va-riously trained languagemodels were evaluated ... linear models local models because they dynamically combine the output of models that use only local features. While it is straightforward to apply the five es-timators to global models in the...