Syntax-Based Translation With Bilingually Lexicalized Synchronous Tree Substitution Grammars

Abstract

Syntax-based models can significantly improve the translation performance due to their grammatical modeling on one or both language side(s). However, the translation rules such as the non-lexical rule “ VP→(x <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">0</sub> x <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> ,VP:x <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> PP:x <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">0</sub> )” in string-to-tree models do not consider any lexicalized information on the source or target side. The rule is so generalized that any subtree rooted at VP can substitute for the nonterminal VP:x <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> . Because rules containing nonterminals are frequently used when generating the target-side tree structures, there is a risk that rules of this type will potentially be severely misused in decoding due to a lack of lexicalization guidance. In this article, inspired by lexicalized PCFG, which is widely used in monolingual parsing, we propose to upgrade the STSG (synchronous tree substitution grammars)-based syntax translation model with bilingually lexicalized STSG. Using the string-to-tree translation model as a case study, we present generative and discriminative models to integrate lexicalized STSG into the translation model. Both small- and large-scale experiments on Chinese-to-English translation demonstrate that the proposed lexicalized STSG can provide superior rule selection in decoding and substantially improve the translation quality.