Stochastic Inversion Transduction Grammars, with Application to Segmentation, Bracketing, and Alignment of Parallel Corpora

Dekai Wu
1995 International Joint Conference on Artificial Intelligence  
We introduce (1) a novel stochavic inversion trans duction grammar formalism for bilingual language modeling of sentence-pairs and (2) the concept of bilingual parsing with potential application to a variety of parallel corpus analysis problems The formalism combines three tactics against the con straints that render finite-state transducers less useful it skips directly to a context-free rather than finite-state base it permits a minimal extra degree of ordering flexibility and its
more » ... c formula tion admits an efficient maximum-likelihood bilin gual parsing algorithm A convenient normal form is shown to exist and we discuss a number of exam pies ot how stochastic inversion transduction grammars bring bilingual constraints to bear upon prob lemalic corpus analysis tasks
dblp:conf/ijcai/Wu95 fatcat:it7vfit3hfbynbmd3eazwkiuim