论文信息 - Stochastic Lexicalized Inversion Transduction Grammar for Alignment

Stochastic Lexicalized Inversion Transduction Grammar for Alignment

We present a version of Inversion Transduction Grammar where rule probabilities are lexicalized throughout the synchronous parse tree, along with pruning techniques for efficient training. Alignment results improve over unlexicalized ITG on short sentences for which full EM is feasible, but pruning seems to have a negative impact on longer sentences.

Daniel Gildea | Hao Zhang | Hao Zhang | D. Gildea

[1] Srinivas Bangalore,et al. Learning Dependency Translation Models as Collections of Finite-State Head Transducers , 2000, Computational Linguistics.

[2] Dekai Wu,et al. Stochastic Inversion Transduction Grammars and Bilingual Parsing of Parallel Corpora , 1997, CL.

[3] Robert L. Mercer,et al. The Mathematics of Statistical Machine Translation: Parameter Estimation , 1993, CL.

[4] Hermann Ney,et al. A Comparative Study on Reordering Constraints in Statistical Machine Translation , 2003, ACL.

[5] Hermann Ney,et al. Improved Statistical Alignment Models , 2000, ACL.

[6] I. Dan Melamed,et al. Multitext Grammars and Synchronous Parsers , 2003, NAACL.

[7] Daniel Gildea,et al. Syntax-Based Alignment: Supervised or Unsupervised? , 2004, COLING.

[8] Kevin Knight,et al. A Syntax-based Statistical Translation Model , 2001, ACL.

[9] Dan Klein,et al. A* Parsing: Fast Exact Viterbi Parse Selection , 2003, NAACL.