论文信息 - Experiments with a noun-phrase driven statistical machine translation system

Experiments with a noun-phrase driven statistical machine translation system

This paper presents a noun phrase driven two-level statistical machine translation system. Noun phrases (NPs) are used as the unit of decomposition to build a two level hierarchy of phrases. English noun phrases are identified using a parser. The corresponding translations are induced using a statistical word alignment model. Identified noun phrase pairs in the training corpus are replaced with a tag to produce a NP tagged corpus. This corpus is then used to extract phrase translation pairs. Both NP translations and NP-tagged phrases are used in a two-level translation decoder: NP translations tag NPs in the first level, where NP-tagged phrases match across NPs to produce translations in the second level. The two-level system shows significant improvements over a baseline SMT system. It also produces longer matching phrases due to the generalization introduced by tagging NPs.

A. Lavie | S. Vogel | Sanjika Hewavitharana

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

[2] Eugene Charniak,et al. A Maximum-Entropy-Inspired Parser , 2000, ANLP.

[3] Salim Roukos,et al. Bleu: a Method for Automatic Evaluation of Machine Translation , 2002, ACL.

[4] Franz Josef Och,et al. Minimum Error Rate Training in Statistical Machine Translation , 2003, ACL.

[5] Philipp Koehn,et al. Noun phrase translation , 2003 .

[6] Robert C. Moore. Learning Translations of Named-Entity Phrases from Parallel Corpora , 2003, EACL.

[7] Daniel Marcu,et al. Statistical Phrase-Based Translation , 2003, NAACL.

[8] S. Vogel,et al. SMT decoder dissected: word reordering , 2003, International Conference on Natural Language Processing and Knowledge Engineering, 2003. Proceedings. 2003.

[9] Hermann Ney,et al. A Systematic Comparison of Various Statistical Alignment Models , 2003, CL.

[10] Alon Lavie,et al. METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments , 2005, IEEvaluation@ACL.

[11] S. Vogel. PESA: Phrase Pair Extraction as Sentence Splitting , 2005, MTSUMMIT.

[12] Ying Zhang,et al. An efficient phrase-to-phrase alignment model for arbitrarily long phrase and large corpora , 2005, EAMT.

[13] David Chiang,et al. A Hierarchical Phrase-Based Model for Statistical Machine Translation , 2005, ACL.