A Comparative Study on English-Chinese Machine Transliteration

被引：0
|
作者：
Gao E. [1 ]
Duan X. [2 ]
机构：
[1] School of Electronic and Information Engineering, Suzhou University of Science and Technology, Suzhou
[2] School of Computer Science and Technology, Soochow University, Suzhou
来源：
Beijing Daxue Xuebao (Ziran Kexue Ban)/Acta Scientiarum Naturalium Universitatis Pekinensis | 2017年 / 53卷 / 02期
关键词：
Deep neural network method; Machine transliteration; Statistical method; Transliteration alignment;
D O I：
10.13209/j.0479-8023.2017.039
中图分类号：
学科分类号：
摘要：
With the aim to study the two main methods on machine transliteration: traditional statistical method and the current prevalent deep neural network method, the authors carry out the comparative study on them with two typical systems per method The experiments show that traditional statistical method and deep neural network method perform comparatively regarding evaluation metrics, while manifest difference on individual transliteration result. A system combination method is proposed to balance the strengths of all systems. Experimental results show that system combination significantly improves the transliteration quality over single system. © 2017 Peking University.
引用
收藏
页码：287 / 294
页数：7
相关论文
共 17 条
  • [11] Bahdanau D., Cho K., Bengio Y., Neural machine translation by jointly learning to align and translate, (2014)
  • [12] Chen B., Zhang M., Li H., Et al., A comparative study of hypothesis alignment and its improvement for machine translation system combination, Proceedings of ACL-IJCNLP, pp. 941-948, (2009)
  • [13] Snover M., Dorr B., Schwartz R., Et al., A study of translation edit rate with targeted human annotation, Proceeding of AMTA, pp. 223-231, (2006)
  • [14] Melamed I.D., Models of translational equivalence among words, Computational Linguistics, 26, 2, pp. 221-249, (2000)
  • [15] He X., Yang M., Gao J., Et al., Indirect HMM-based hypothesis alignment for combining outputs from machine translation systems, Proceedings of EMNLP, pp. 98-107, (2008)
  • [16] Zeiler M.D., ADADELTA: an adaptive learning rate method, (2012)
  • [17] Cheng Y., Shen S., He Z.J., Et al., Agreement-based joint training for bidirectional attention-based neural machine translation, Proceedings of IJCAI, pp. 2761-2767, (2016)
12