PESA: Phrase Pair Extraction as Sentence Splitting

Stephan Vogel


Abstract
Most statistical machine translation systems use phrase-to-phrase translations to capture local context information, leading to better lexical choice and more reliable local reordering. The quality of the phrase alignment is crucial to the quality of the resulting translations. Here, we propose a new phrase alignment method, not based on the Viterbi path of word alignment models. Phrase alignment is viewed as a sentence splitting task. For a given spitting of the source sentence (source phrase, left segment, right segment) find a splitting for the target sentence, which optimizes the overall sentence alignment probability. Experiments on different translation tasks show that this phrase alignment method leads to highly competitive translation results.
Anthology ID:
2005.mtsummit-papers.33
Volume:
Proceedings of Machine Translation Summit X: Papers
Month:
September 13-15
Year:
2005
Address:
Phuket, Thailand
Venue:
MTSummit
SIG:
Publisher:
Note:
Pages:
251–258
Language:
URL:
https://aclanthology.org/2005.mtsummit-papers.33
DOI:
Bibkey:
Cite (ACL):
Stephan Vogel. 2005. PESA: Phrase Pair Extraction as Sentence Splitting. In Proceedings of Machine Translation Summit X: Papers, pages 251–258, Phuket, Thailand.
Cite (Informal):
PESA: Phrase Pair Extraction as Sentence Splitting (Vogel, MTSummit 2005)
Copy Citation:
PDF:
https://aclanthology.org/2005.mtsummit-papers.33.pdf