Syntax-based Rewriting for Simultaneous Machine Translation

Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 55–64, Lisbon, Portugal, 17-21 September 2015. c⃝2015 Association for Computational Linguistics. Syntax-based Rewriting for Simultaneous Machine Translation He He Computer Science University of Maryland hhe@cs.umd.edu Alvin Grissom II, Jordan Boyd-Graber Computer Science University of Colorado {Alvin.Grissom, Jordan.Boyd.Graber} @colorado.edu Hal Daumé III Computer Science and UMIACS University of Maryland hal@cs.umd.edu Abstract Divergent word order between languages causes delay in simultaneous machine translation. We present a sentence rewrit- ing method that generates more mono- tonic translations to improve the speed- accuracy tradeoff. We design grammati- cality and meaning-preserving syntactic transformation rules that operate on con- stituent parse trees. We apply the rules to reference translations to make their word order closer to the source language word order. On Japanese-English transla- tion (two languages with substantially dif- ferent structure), incorporating the rewrit- ten, more monotonic reference translation into a phrase-based machine translation system enables better translations faster than a baseline system that only uses gold reference translations. 1 Introduction Simultaneous interpretation is challenging because it demands both quality and speed. Conventional batch translation waits until the entire sentence is completed before starting to translate. This merely optimizes translation quality and often introduces undesirable lag between the speaker and the audi- ence. Simultaneous interpretation instead requires a tradeoff between quality and speed. A common strategy is to translate independently translatable segments as soon as possible. Various segmenta- tion methods (Fujita et al., 2013; Oda et al., 2014) reduce translation delay; they are limited, however, by the unavoidable word reordering between lan- guages with drastically different word orders. We show an example of Japanese-English translation in Figure 1. Consider the batch translation: in En- glish, the verb change comes immediately after the subject We, whereas in Japanese it comes at the end of the sentence; therefore, to produce an intelligible English sentence, we must translate the object after the final verb is observed, resulting in one large and painfully delayed segment. To reduce structural discrepancy, we can apply syntactic transformations to make the word order of one language closer to the other. Consider the monotone translation in Figure 1. By passivizing the English sentence, we can cache the subject and begin translating before observing the final verb. Furthermore, by using the English possessive, we mimic the order of the Japanese genitive construc- tion. These transformations enable us to divide the input into shorter segments, thus reducing transla- tion delay. To produce such monotone translations, a straightforward approach is to incorporate inter- pretation data into the learning of a machine trans- lation (MT) system, because human interpreters use a variety of strategies (Shimizu et al., 2014; Camayd-Freixas, 2011; Tohyama and Matsubara, 2006) to fine-tune the word order. Shimizu et al. (2013) shows that this approach improves the speed-accuracy tradeoff. However, existing paral- lel simultaneous interpretation corpora (Shimizu et al., 2014; Matsubara et al., 2002; Bendazzoli and Sandrelli, 2005) are often small, and collecting new data is expensive due to the inherent costs of …

Content truncated to 500 words