The Research on Reordering Rule of Chinese-Mongolian Statistical Machine Translation

Abstract:

There are a lot of word order errors that occur in the Chinese-Mongolian statistical machine translation system, so we proposed Chinese sentence reordering method based on the Mongolian word order. In this paper we first introduce the form and the tagset of reordering rules. We mainly introduce the reordering rules related to the verb phrase, prepositional phrase and subject-predicate phrase. Finally, we give out the experimental results. It is proved by experiment that the performance of the Chinese-Mongolian machine translation system can be improved using these reordering rules.

• Periodical: Advanced Materials Research (Volumes 268-270)
• Pages: 2185-2190
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.268-270.2185
• Online since: July 2011
• Authors: Si Ri Gu Leng Wang, Qin Tu Si, Urtu Nasun
• Keywords: Chinese-Mongolian, Reordering Rule, Statistical Machine Translation, Tagset

References

[1] Yushiwen etc: Modern Chinese grammar information dictionary explanation [M]. Beijing: Peking University publishing house, (1998).

[2] Nasun-urtu: Information technology Information processing in Mongolian POS tagset, The National Standard (2008).

[3] Nasun-urtu: Mongolian grammar information dictionary frame design[D]. Inner Mongolia university, (2000).

[4] Badma Odser: Research on transition rules of facing machine translation Chinese-Mongolian[M]. Hohhot: Inner Mongolia education publishing house, (2006).

[5] DabhorBayar. Research on automatic recognition for base verb phrase in Mongolian language [D]: Inner Mongolia University, (2005).

[6] Wang siriguleng, Siqintu, Nasun-urt: Phrase-Based Chinese Mongolian Statistical Machine Translation[J]. Computer Engineering and Applications, No. 14, (2010 ), pp.138-142.