Rule Selection with Soft Syntactic Features for String-to-Tree Statistical Machine Translation

Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 1095–1101, Lisbon, Portugal, 17-21 September 2015. c⃝2015 Association for Computational Linguistics. Rule Selection with Soft Syntactic Features for String-to-Tree Statistical Machine Translation Fabienne Braune and Nina Seemann and Alexander Fraser CIS, Ludwig-Maximilians-Universit¨at M¨unchen Oettingenstraße 67, 80538 M¨unchen, Germany [braunefe|seemanna]@ims.uni-stuttgart.de fraser@cis.uni-muenchen.de Abstract In syntax-based machine translation, rule selection is the task of choosing the cor- rect target side of a translation rule among rules with the same source side. We de- fine a discriminative rule selection model for systems that have syntactic annota- tion on the target language side (string- to-tree). This is a new and clean way to integrate soft source syntactic constraints into string-to-tree systems as features of the rule selection model. We release our implementation as part of Moses. 1 Introduction Syntax-based machine translation is well known for its ability to handle non-local reordering. Syntax-based models either use linguistic annota- tion on the source language side (Huang, 2006; Liu et al., 2006), target language side (Galley et al., 2004; Galley et al., 2006) or are syntactic in a structural sense only (Chiang, 2005). Recent shared tasks have shown that systems integrat- ing information on the target language side, also called string-to-tree systems, achieve the best per- formance on several language pairs (Bojar et al., 2014). At the same time, soft syntactic features significantly improve the translation quality of hi- erarchical systems (Hiero) as shown in (Marton et al., 2012; Chiang, 2010; Liu et al., 2011; Cui et al., 2010). Improving the performance of string- to-tree systems through the integration of soft syn- tactic constraints on the source language side is therefore an interesting task. So far, all approaches on this topic include soft syntactic constraints into the rules of string-to-tree (Zhang et al., 2011; Huck et al., 2014) or string- to-dependency (Huang et al., 2013) systems and define heuristics to determine to what extent these constituents match the syntactic structure of the source sentence. We propose a novel way to in- tegrate soft syntactic constraints into a string-to- tree system. We define a discriminative rule se- lection model for string-to-tree machine transla- tion. We consider rule selection as a multi-class classification problem where the task is to select the correct target side of a rule given its source side as well as contextual information about the source sentence and the considered rule. So far, such models have been applied to systems without syntactic annotation on the target language side. He et al. (2008), He et al. (2010) and Cui et al. (2010) apply such rule selection models to hier- archical machine translation, Liu et al. (2008) to tree-to-string systems and Zhai et al. (2013) to systems based on predicate argument structures. When target side syntactic annotations are taken into account, the task of rule selection has to be reformulated (see Section 2) while the same type of model can be used in approaches without target annotations. This work is the first attempt to define a …

Content truncated to 500 words