Improving Translation Selection with a New Translation Model Trained by Independent Monolingual Corpora

1 Computational Linguistics and Chinese Language Processing Vol. 6, No. 1, February 2001, pp. 1-26 © Computational Linguistics Society of R.O.C. Improving Translation Selection with a New Translation Model Trained by Independent Monolingual Corpora Ming Zhou*, Yuan Ding+1, Changning Huang* Abstract We propose a novel statistical translation model to improve translation selection of collocation. In the statistical approach that has been popularly applied for translation selection, bilingual corpora are used to train the translation model. However, there exists a formidable bottleneck in acquiring large-scale bilingual corpora, in particular for language pairs involving Chinese. In this paper, we propose a new approach to training the translation model by using unrelated monolingual corpora. First, a Chinese corpus and an English corpus are parsed with dependency parsers, respectively, and two dependency triple databases are generated. Then, the similarity between a Chinese word and an English word can be estimated using the two monolingual dependency triple databases with the help of a simple Chinese-English dictionary. This cross-language word similarity is used to simulate the word translation probability. Finally, the generated translation model is used together with the language model trained with the English dependency database to realize translation of Chinese collocations into English. To demonstrate the effectiveness of this method, we performed various experiments with verb-object collocation translation. The experiments produced very promising results. Keywords: Translation selection, Statistical machine translation, Chinese-English machine translation, Cross language word similarity 1. Introduction Selecting the appropriate word translation among several options is a key technology of machine translation. For example, the Chinese verb “订” is translated in different ways in * Microsoft Research, Asia. + Tsinghua University. 1 Currently is studying at University of Pennsylvania as Ph.D. student. This work was done while visiting Microsoft Research Asia as a visiting student. 2 M. Zhou et al. terms of objects, as shown in the following: 订 报纸 →subscribe to a newspaper 订 计划 →make a plan 订 旅馆 →book a hotel 订 车票 →reserve a ticket 订 时间 →determine the time In recent years, there has been increasing interest in applying statistical approaches to various machine translation tasks, from MT system mechanisms to translation knowledge acquisition. For translation selection, most researches applied statistical translation models. In such statistical translation models, to get the word translation probability as well as translation templates, bilingual corpora are needed. However, for quite a few languages, large bilingual corpora rarely exist, while large monolingual corpora are easy to acquire. It will be helpful to alleviate the burden of collecting bilingual corpus if we can use monolingual corpora to estimate the translation model and find alternative to translation selection. We propose a novel approach to this problem in the Chinese-English machine translation module which is to be used for cross-language information retrieval. Our method is based on the intuition that although the Chinese language and the English language have different definitions of dependency relations, the main dependency relations like subject-verb, verb-object, adjective-noun and adverb-verb tend to have strongly direct correspondence. This assumption can be used …

Content truncated to 500 words