Paper: Pseudo-Word for Phrase-Based Machine Translation

ACL ID P10-1016
Title Pseudo-Word for Phrase-Based Machine Translation
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2010
Authors

The pipeline of most Phrase-Based Statistical Machine Translation (PB-SMT) systems starts from automatically word aligned parallel cor- pus. But word appears to be too fine-grained in some cases such as non-compositional phrasal equivalences, where no clear word alignments exist. Using words as inputs to PB- SMT pipeline has inborn deficiency. This pa- per proposes pseudo-word as a new start point for PB-SMT pipeline. Pseudo-word is a kind of basic multi-word expression that character- izes minimal sequence of consecutive words in sense of translation. By casting pseudo-word searching problem into a parsing framework, we search for pseudo-words in a monolingual way and a bilingual synchronous way. Ex- periments show that pseudo-word significantly outperforms word for PB-SMT ...