Repairing Incorrect Translation with Examples

International Joint Conference on Natural Language Processing, pages 967–971, Nagoya, Japan, 14-18 October 2013. Repairing Incorrect Translation with Examples Junguo Zhu, Muyun Yang, Sheng Li, Tiejun Zhao School of Computer Science and Technology, Harbin Institute of Technology Harbin, China {ymy, jgzhu}@mtlab.hit.edu.cn; {lisheng,tjzhao}@hit.edu.cn Abstract This paper proposes an example driven ap- proach to improve the quality of MT system outputs. Specifically, We extend the system combination method in SMT to combine the examples by two strategies: 1) estimating the confidence of examples by the similarity be- tween source input and the source part of ex- amples; 2) approximating target word posteri- or probability by the word alignments of the bilingual examples. Experimental results show a significant improvement of 0.64 BLEU score as compared to one online translation service (Google Translate). 1 Introduction Statistical Machine Translation (SMT), state-of- the-art solution, has remarkable success with the support of the large-scale bilingual corpora to boost the translation quality at present. However, due to the long tail effect of human language, statistical anomalies in the training data can cause that tons of desired translation knowledge could not be statistically learned from the large- scale bilingual corpora. As a result, bulks of the specific translation requirements not well ad- dressed still perplex machine translation academ- ia and industry. Combining the examples with machine trans- lations output is a good solution to improve translation quality for this issue. Several methods have been proposed in recent years. One ap- proach tries to replace relevant chunks, taking advantage of Translation Memory (TM). Its mo- tivation is to store and to retrieve similar transla- tion examples for a given input, then to avail of examples to replace the similar chunks into the input by the threshold of similar score (Smith and Clark, 2009; Koehn and Senellart,2010) or by the decision of an automatic classifier (He at al., 2010; Ma et al., 2011). Another approach tries to enhance phrase table of SMT, integrating collected bilingual pairs into the phrase table (Biҫici and Clark, 2009; Simardand Isabelle, 2010; DauméIII and Jagarlamudi, 2011). Different to the above studies in which the EBMT and SMT function in a pipeline style, the work in this paper tries to integrate the SMT re- sults and translation examples in a unified framework. In parallel to the system combination in SMT, we try to integrate the translation exam- ples into the confusion network, allowing each word in both SMT results and examples to com- pete for the optimal output. In order to achieve the goal, the proposed method introduces some new features to bridge the statistical and example translation. This paper presents an approach to repairing the translation errors via retrieving translation examples from examples corpus. The effective- ness of our method is validated on the standard test set of Olympics task in IWSLT 2012 Evalua- tion Campaign. Experimental results show that an absolute increase of 0.64 BLEU score is ob- served after repairing original translations. This significant improvement suggests the proposed strategy as a promising solution to …

Content truncated to 500 words