A Bilingual Graph-Based Semantic Model for Statistical Machine Translation

Wang, Rui; Zhao, Hai; Ploux, Sabine; Lu, Bao-Liang; Utiyama, Masao

A Bilingual Graph-Based Semantic Model for Statistical Machine Translation

Rui Wang, Hai Zhao, Sabine Ploux, Bao-Liang Lu, Masao Utiyama

Download BibTeX Cite

Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence. Pages 2950-2955.

Abstract

Most existing bilingual embedding methods for Statistical Machine Translation (SMT) suffer from two obvious drawbacks. First, they only focus on simple context such as word count and co-occurrence in document or sliding window to build word embedding, ignoring latent useful information from selected context. Second, word sense but not word form is supposed to be the minimal semantic unit while most existing works are still for word representation. This paper presents Bilingual Graph-based Semantic Model (BGSM) to alleviate such shortcomings. By means of maximum complete sub-graph (clique) for context selection, BGSM is capable of effectively modeling word sense representation instead of the word form itself. The proposed model is applied to phrase pair translation probability estimation and generation for SMT. The empirical results show that BGSM can enhance SMT both in performance (up to +1.3 BLEU) and efficiency in comparison against existing methods.

Rui Wang, Hai Zhao, Sabine Ploux, Bao-Liang Lu, and Masao Utiyama. 2016. A Bilingual Graph-Based Semantic Model for Statistical Machine Translation. In Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-16. IJCAI, 2950–2955. https://ijcai.org/proceedings/2016/419

@inproceedings{ijcai2016p419,
  title     = {A Bilingual Graph-Based Semantic Model for Statistical Machine Translation},
  author    = {Wang, Rui and Zhao, Hai and Ploux, Sabine and Lu, Bao-Liang and Utiyama, Masao},
  booktitle = {Proceedings of the Twenty-Fifth International Joint Conference on
               Artificial Intelligence, {IJCAI-16}},
  publisher = {AAAI Press / International Joint Conferences on Artificial Intelligence},
  editor    = {Subbarao Kambhampati},
  pages     = {2950--2955},
  year      = {2016},
  month     = {7},
  url       = {https://ijcai.org/proceedings/2016/419},
}

TY  - CPAPER
TI  - A Bilingual Graph-Based Semantic Model for Statistical Machine Translation
AU  - Wang, Rui
AU  - Zhao, Hai
AU  - Ploux, Sabine
AU  - Lu, Bao-Liang
AU  - Utiyama, Masao
T2  - Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-16
PB  - AAAI Press / International Joint Conferences on Artificial Intelligence
PY  - 2016
SP  - 2950
EP  - 2955
UR  - https://ijcai.org/proceedings/2016/419
ER  -