Do we need phrases? Challenging the conventional wisdom in Statistical Machine Translation

Proceedings of the Human Language Technology Conference of the North American Chapter of the ACL, pages 9–16, New York, June 2006. c⃝2006 Association for Computational Linguistics Do we need phrases? Challenging the conventional wisdom in Statistical Machine Translation Chris Quirk and Arul Menezes Microsoft Research One Microsoft Way Redmond, WA 98052 USA {chrisq,arulm}@microsoft.com Abstract We begin by exploring theoretical and practical issues with phrasal SMT, several of which are addressed by syntax-based SMT. Next, to address problems not handled by syntax, we propose the concept of a Minimal Translation Unit (MTU) and develop MTU sequence models. Finally we incorporate these models into a syntax-based SMT system and demonstrate that it improves on the state of the art translation quality within a theoretically more desirable framework. 1. Introduction The last several years have seen phrasal statistical machine translation (SMT) systems outperform word-based approaches by a wide margin (Koehn 2003). Unfortunately the use of phrases in SMT is beset by a number of difficult theoretical and practical problems, which we attempt characterize below. Recent research into syntax-to based SMT (Quirk and Menezes 2005; Chiang 2005) has produced promising results in addressing some of the problems; research motivated by other statistical models has helped to address others (Banchs et al. 2005). We refine and unify two threads of research in an attempt to address all of these problems simultaneously. Such an approach proves both theoretically more desirable and empirically superior. In brief, Phrasal SMT systems employ phrase pairs automatically extracted from parallel corpora. To translate, a source sentence is first partitioned into a sequence of phrases I = s1…sI. Each source phrase si is then translated into a target phrase ti. Finally the target phrases are permuted, and the translation is read off in order. Beam search is used to approximate the optimal translation. We refer the reader to Keohn et al. (2003) for a detailed description. Unless otherwise noted, the following discussion is generally applicable to Alignment Template systems (Och and Ney 2004) as well. 1.1. Advantages of phrasal SMT Non-compositionality Phrases capture the translations of idiomatic and other non-compositional fixed phrases as a unit, side-stepping the need to awkwardly reconstruct them word by word. While many words can be translated into a single target word, common everyday phrases such as the English password translating as the French mot de passe cannot be easily subdivided. Allowing such translations to be first class entities simplifies translation implementation and improves translation quality. Local re-ordering Phrases provide memorized re-ordering decisions. As previously noted, translation can be conceptually divided into two steps: first, finding a set of phrase pairs that simultaneously covers the source side and provides a bag of translated target phrases; and second, picking an order for those target phrases. Since phrase pairs consist of memorized substrings of the training data, they are very likely to produce correct local re- orderings. Contextual information Many phrasal translations may be easily subdivided into word-for-word translation, for instance the English phrase the cabbage may be translated word-for-word …

Content truncated to 500 words