mt03-tutorial

Introduction toStatistical Machine TranslationKenji YamadaXerox Research Centre EuropeWhat is Statistical MT?• Traditional MT = rule-based Human written (several years)• Statistical MT = data-drivenStatistical ModelParameter estimation (learn from input/output pairs)Translation = decodingStatistical MT as …• Instance of Machine Learning problem– Learn function of French English• A kind of Speech Recognition– Audio signal word sequence– Noisy channel modelààNoisy Channel ModelLanguage Model Translation Modelchannelsource e fP(f|e)P(e)observed bestdecodere fargmax P(e|f) = argmax P(f|e)P(e)eeDecompose a complex problem• Traditional (rule-based) MT– Analyze and generate– Morphology, syntax, semantics, …• Statistical MT– Mathematically easy decomposition– Utilize existing parameter estimation algorithm– Simple model, huge training data(rely on computational power)Translation Models• Word-based Models– IBM Model (model 1-5) [Brown, et al. 1993]• Phrase-– Wang’s model [Wang and Waibel, 1998]– Alignment Templates [Och et al., 1999]• Syntax-based Models– Inversion Transduction Grammar [Wu, 1997]– Head Automata [Alshawi et al., 2000]– Tree-to-string model [Yamada and Knight, 2001]– Tree-to-tree models [Hajic et al, 2002], [Glidea 2003]IBM Model (word-based model)Mary did not slap the green witchfertility n(3|slap)Mary not slap slap slap the green witch null-insertionP(NULL)Mary not slap slap slap NULL the green ...