N-gram-based Tense Models for Statistical Machine Translation

Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pages 276–285, Jeju Island, Korea, 12–14 July 2012. c⃝2012 Association for Computational Linguistics N-gram-based Tense Models for Statistical Machine Translation Zhengxian Gong1 Min Zhang2 Chewlim Tan3 Guodong Zhou1∗ 1 School of Computer Science and Technology, Soochow University, Suzhou, China 215006 2 Human Language Technology, Institute for Infocomm Research, Singapore 138632 3 School of Computing, National University of Singapore, Singapore 117417 {zhxgong, gdzhou}@suda.edu.cn mzhang@i2r.a-star.edu.sg tancl@comp.nus.edu.sg Abstract Tense is a small element to a sentence, how- ever, error tense can raise odd grammars and result in misunderstanding. Recently, tense has drawn attention in many natural language processing applications. However, most of current Statistical Machine Translation (SMT) systems mainly depend on translation model and language model. They never consider and make full use of tense information. In this pa- per, we propose n-gram-based tense models for SMT and successfully integrate them in- to a state-of-the-art phrase-based SMT system via two additional features. Experimental re- sults on the NIST Chinese-English translation task show that our proposed tense models are very effective, contributing performance im- provement by 0.62 BLUE points over a strong baseline. 1 Introduction For many NLP applications, such as event extraction and summarization, tense has been regarded as a key factor in providing temporal order. However, tense information has been largely overlooked by current SMT research. Consider the following example: SRC: ù ‘ B$ ´ eÔ � (J , Ø U ‡N y3 � œ³ , • ™ ‡N ¥I † î† m � ºŠ 'X " REF:The embargo is a result of the Cold War and does not reflect the present situation nor the partnership between China and the EU. MOSES: the embargo is the result of the cold war, not reflect the present situation, it did not reflect the partnership with the european union. ∗*Corresponding author. Although the translated text produced by Moses1 is understandable, it has very odd tense combination from the grammatical aspect, i.e. with tense incon- sistency (is/does in REF vs. is/did in Moses). Ob- viously, slight modification, such as changing “is” into “was”, can much improve the readability of the translated text. It is also interesting to note that such modification can much affect the evaluation. If we change “did” to “does”, the BLEU-4 score increases from 22.65 to 27.86 (as matching the 4-gram “does not reflect the” in REF). However, if we change “is” to “was”, the BLEU score decreases from 22.65 to 21.44. The above example seems special. To testify its impact on SMT in wider range, we design a special experiment based on the 2005 NIST MT data (see section 6.1). This data has 4 references. We choose one reference and modify its sentences with error tense2. After that, we use other 3 references to mea- sure this reference. The modified reference leads to a sharp drop in BLEU-4 score, from 52.46 to 50.27 in all. So it is not a random phenomenon that tense …

Content truncated to 500 words