Cross-language Projection of Dependency Trees with Constrained Partial Parsing for Tree-to-Tree Machine Translation

Proceedings of the First Conference on Machine Translation, Volume 1: Research Papers, pages 1–11, Berlin, Germany, August 11-12, 2016. c⃝2016 Association for Computational Linguistics Cross-language Projection of Dependency Trees with Constrained Partial Parsing for Tree-to-Tree Machine Translation Yu Shen1, Chenhui Chu2∗, Fabien Cromieres2 and Sadao Kurohashi1 1Graduate School of Informatics, Kyoto University 2Japan Science and Technology Agency {shen-yu,kuro}@nlp.ist.i.kyoto-u.ac.jp {chu,fabien}@pa.jst.jp Abstract Tree-to-tree machine translation (MT) that utilizes syntactic parse trees on both source and target sides suffers from the non-isomorphism of the parse trees due to parsing errors and the difference of an- notation criterion between the two lan- guages. In this paper, we present a method that projects dependency parse trees from the language side that has a high quality parser, to the side that has a low qual- ity parser, to improve the isomorphism of the parse trees. We first project a part of the dependencies with high confidence to make a partial parse tree, and then com- plement the remaining dependencies with partial parsing constrained by the already projected dependencies. MT experiments verify the effectiveness of our proposed method. 1 Introduction According to how syntactic parse trees are used in machine translation (MT), there are 4 types of MT approaches: string-to-string that does not use parse trees (Chiang, 2005; Koehn et al., 2007), string-to-tree that uses parse trees on the target side (Galley et al., 2006; Shen et al., 2008), tree- to-string that uses parse trees on the source side (Quirk et al., 2005; Liu et al., 2006; Mi and Huang, 2008), and tree-to-tree that uses parse trees on both sides (Zhang et al., 2008; Richardson et al., 2015). Intuitively, the tree-to-tree approach seems to be the most appropriate. The reason is that it could preserve the structure information on both sides, which leads to fluent and accurate translations. In practice, however, good quality parsers on both the source and target sides are difficult to ac- ∗Corresponding author. quire. In many cases, the parsing quality of one side is much higher than that of the other side, because the higher quality side has a well anno- tated treebank or is linguistically easier to parse. For example, in the case of Japanese-Chinese MT that we study in this paper, the head-final charac- teristic of Japanese (Isozaki et al., 2010) makes the dependency parsing for Japanese much eas- ier than that of Chinese. Currently, the depen- dency parsing accuracy of Japanese is over 90% (Kawahara and Kurohashi, 2006), while the Chi- nese parsing accuracy is less than 80% (Shen et al., 2012). Another problem is the annotation cri- terion difference of the treebanks in different lan- guages, which are used for training the parsers. For example, the dependency annotations of noun phrases and coordination could be different among different languages. For example, in Japanese, noun phrases and coordination are annotated as modifier-head dependencies (Kawahara and Kuro- hashi, 2006), while in Chinese they are annotated as sibling dependencies (Shen et al., 2012). These two problems lead to the parse difference between …

Content truncated to 500 words