Chiang 2005

Citation

Chiang, D. 2005. A Hierarchical Phrase-Based Model for Statistical Machine Translation. In Proceedings of the 43rd Annual Meeting of the ACL, pp. 263–270, Ann Arbor. Association for Computational Linguistics.

Online version

Information Sciences Institute, University of Southern California

Summary

This paper presents a statistical phrase-based machine translation model that uses hierarchical phrases (phrases that contain subphrases). The model is formally syntax-based because it uses Synchronous Context-Free Grammars (synchronous CFG) but not linguistically syntax-based because the grammar is learned from a parallel text without using any linguistic annotations or assumptions. Using BLEU as a metric, it is shown to outperform previous state-of-the-art phrase-based systems.

The hierarchical model is motivated by the inability of conventional phrase-based models to learn reorderings of phrases (and not only local reorderings of words). For example, considering the following Mandarin sentence:

Aozhou    shi yu   Bei   Han   you  bangjiao             de   shaoshu guojia    zhiyi
Australia is  with North Korea have diplomatic relations that few     countries one of

(Australia is one of the few countries that have diplomatic relations with North Korea)

the typical output of a conventional phrase-based system would be:

Australia is diplomatic relations with North Korea is one of the few countries

because it is able to do the local reorderings of "diplomatic ... Korea" and "one ... countries" but fails to perform the inversion of the two groups.

The general idea is to have pairs of hierarchical phrases that consist of both words and subphrases. These pairs are formally defined as productions of a synchronous CFG. The following pairs along with conventional prase pairs are sufficient to translate the previous example correctly:

$X\rightarrow \left\langle yu\;X_{[1]}\;you\;X_{[2]}\;,\;have\;X_{[1]}\;with\;X_{[1]}\right\rangle <[1]de[2],the[2]that[1]><[1]zhiyi,oneof[1]>$