Hybrid Combination of Machine Translation with Part-of-Speech Analysis

Abstract:

Hypothesis combination is a main method to improve the performance of machine translation (MT) system. The state-of-the-arts strategies include sentence-level and word-level methods, which has its own advantages and disadvantages. And, the current strategies mainly depends on the statistical method with little guidance from the rich linguistic knowledge. This paper propose hybrid framework to combine the ability of the sentence-level and word-level methods. In word-level stage, the method select the well translated words according to its part-of-speech and translation ability of this part-of-speech of the MT system which generate this word. The experimental results with different MT systems proves the effectiveness of this approach.

• Periodical: Applied Mechanics and Materials (Volumes 416-417)
• Pages: 1552-1557
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.416-417.1552
• Online since: September 2013
• Authors: Xiao Xu Hu
• Keywords: Hypothesis Combination, Machine Translation, Sentence-Level, Translation Ability of Part-of-Speech, Word-Level

References

[1] Philipp Koehn, Hieu Hoang, Alexandra Birch, ChrisCallison-Burch, Marcello Federico, Nicola Bertoldi, Brooke Cowan, Wade Shen, Christine Moran, Richard Zens, Chris Dyer, Ondrej Bojar, Alexandra Constrantin, and Evan Herbst. 2007. Moses: Open source toolkit for statistical machine translation [C]. In: Proc. of 45th Meeting of the ACL.

DOI: 10.3115/1557769.1557821

[2] David Chiang, 2007. Hierarchical phrase-based translation [J]. In Computational Linguistics, 33(2): 201-228.

DOI: 10.1162/coli.2007.33.2.201

[3] Michel Galley, Jonathan Graehl, Kevin Knight, Daniel Marcu, Steve DeNeefe, Wei Wang, and Ignacio Thayer. 2006. Scalable inferences and training of context-rich syntax translation models[c]. In: Proc. of 44th COLING/ACL.

DOI: 10.3115/1220175.1220296

[4] Bo Wang, Tiejun Zhao, Muyun Yang, Hongfei Jiang and Sheng Li. Stability vs. Effectiveness: Improved Sentence-level Combination of Machine Translation Based on Weighted MBR[c], International Conference on Asian Language Processing (IALP 2009), Singapore, Dec 7-9, (2009).

DOI: 10.1109/ialp.2009.17

[5] Antti-Veikko I. Rosti, Necip Fazil Ayan, Bing Xiang, Spyros Matsoukas, Richard Schwartz, and Bonnie Dorr. 2007. Combining outputs from multiple machine translation systems[c]. In: Proc. of the HLT/NAACL, (2007).

[6] Antti-Veikko I. Rosti, Spyros Matsoukas, and Ricahrd Schwartz. 2007. Improved Word-Level System Combination for Machine Translation[c]. In: Proc. of the 45th ACL, (2007).

[7] Matusov Evgeny, Nicola Ueffing, and Hermann Ney. 2006. Computing consensus translation from multiple machine translation systems using enhanced hypotheses alignment[c]. In Proc. of EACL, (2006).

[8] K. -C. Sim, W. Byrne, M. Gales, H. Sahbi, and P.C. Woodland. 2007. Consensus network decoding for statistical machine translation system combination[c]. In IEEE Conference on Acoustics, Speech and Signal Processing, (2007).

DOI: 10.1109/icassp.2007.367174

[9] Roy Tromble, Shankar Kumar, Franz Och, Wolfgang Macherey, Lattice Minimum Bayes-Risk Decoding for Statistical Machine Translation[c], Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing, pp.620-629.

DOI: 10.3115/1613715.1613792

[10] Kishore Papieni, Salim Roukos, Todd Ward, Wei-Jing Zhu. 2002. BLEU: a method for automatic evaluation of machine translation[c], In: Proc. of the 40th Meeting of the ACL.

DOI: 10.3115/1073083.1073135

[11] Ming Zhou, Bo Wang, Shujie Liu, Mu Li, Dongdong Zhang, Tiejun Zhao. Diagnostic Evaluation of Machine Translation Systems Using Automatically Constructed Linguistic Check-Points [c]. In Proceedings of the 22nd International Conference on Computational Linguistics (Coling 2008), Manchester, UK, pp.1121-1128, August (2008).

DOI: 10.3115/1599081.1599222