Two Languages are Better than One (for Syntactic Parsing)

Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing, pages 877–886, Honolulu, October 2008. c⃝2008 Association for Computational Linguistics Two Languages are Better than One (for Syntactic Parsing) David Burkett and Dan Klein Computer Science Division University of California, Berkeley {dburkett,klein}@cs.berkeley.edu Abstract We show that jointly parsing a bitext can sub- stantially improve parse quality on both sides. In a maximum entropy bitext parsing model, we define a distribution over source trees, tar- get trees, and node-to-node alignments be- tween them. Features include monolingual parse scores and various measures of syntac- tic divergence. Using the translated portion of the Chinese treebank, our model is trained iteratively to maximize the marginal likeli- hood of training tree pairs, with alignments treated as latent variables. The resulting bi- text parser outperforms state-of-the-art mono- lingual parser baselines by 2.5 F1 at predicting English side trees and 1.8 F1 at predicting Chi- nese side trees (the highest published numbers on these corpora). Moreover, these improved trees yield a 2.4 BLEU increase when used in a downstream MT evaluation. 1 Introduction Methods for machine translation (MT) have increas- ingly leveraged not only the formal machinery of syntax (Wu, 1997; Chiang, 2007; Zhang et al., 2008), but also linguistic tree structures of either the source side (Huang et al., 2006; Marton and Resnik, 2008; Quirk et al., 2005), the target side (Yamada and Knight, 2001; Galley et al., 2004; Zollmann et al., 2006; Shen et al., 2008), or both (Och et al., 2003; Aue et al., 2004; Ding and Palmer, 2005). These methods all rely on automatic parsing of one or both sides of input bitexts and are therefore im- pacted by parser quality. Unfortunately, parsing gen- eral bitexts well can be a challenge for newswire- trained treebank parsers for many reasons, including out-of-domain input and tokenization issues. On the other hand, the presence of translation pairs offers a new source of information: bilin- gual constraints. For example, Figure 1 shows a case where a state-of-the-art English parser (Petrov and Klein, 2007) has chosen an incorrect structure which is incompatible with the (correctly chosen) output of a comparable Chinese parser. Smith and Smith (2004) previously showed that such bilin- gual constraints can be leveraged to transfer parse quality from a resource-rich language to a resource- impoverished one. In this paper, we show that bilin- gual constraints and reinforcement can be leveraged to substantially improve parses on both sides of a bitext, even for two resource-rich languages. Formally, we present a log-linear model over triples of source trees, target trees, and node-to- node tree alignments between them. We consider a set of core features which capture the scores of monolingual parsers as well as measures of syntactic alignment. Our model conditions on the input sen- tence pair and so features can and do reference input characteristics such as posterior distributions from a word-level aligner (Liang et al., 2006; DeNero and Klein, 2007). Our training data is the translated section of the Chinese treebank (Xue et …

Content truncated to 500 words