|
|
|
| Chinese Vietnamese Neural Machine Translation Method Based on Dependency Graph Network |
| PU Liuqing1,2, YU Zhengtao1,2, WEN Yonghua1,2, GAO Shengxiang1,2 , LIU Yiyang1,2 |
1. School of Information Engineering and Automation, Kunming University of Science and Technology, Kunming,Yunnan 650500,China;
2. Yunnan Key Laboratory of Artificial Intelligence,Kunming University of Science and Technology, Kunming,Yunnan 650500,China |
|
|
|
|
Abstract Chinese Vietnamese neural machine translation is a typical lowresource task. Due to the lack of largescale parallel corpus, the model may not learn enough bilingual differences and the translation quality is not good. A ChineseVietnamese neural machine translation method based on dependency graph network is proposed. This method uses dependency syntactic relations to construct a dependency graph network and incorporates neural machine translation. In the framework of the Transformer, a graph encoder is introduced to capture the dependency structure diagram of the source language, which is then integrated with the sequence embedding via multihead attention mechanism. When decoding , structured and sequence encoding are used to guide the decoder to generate translations. The experimental results show that in the ChineseVietnamese translation task, incorporating the dependency syntax graph can improve the performance of the translation model.
|
|
Received: 09 November 2020
|
|
|
|
|
|
［1］Liu Y, Liu Q, Lin S. Tree-to-String alignment template for statistical machine translation［C］//Proceedings of the ACL, 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics, DBLP, 2006.
［2］He J, Yu Z,Lv C, et al. Language post positioned characteristic based Chinese-Vietnamese statistical machine translation method［C］//Proceedings of the International Conference on Asian Language Processing. IEEE, 2018.
［3］Eriguchi A, Hashimoto K, Tsuruoka Y. Tree-to-Sequence attentional neural machine translation［C］//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, 2016.
［4］Bahdanau D, Cho K, Bengio Y. Neural machine translation by jointly learning to align and translate ［EB/OL］. https://arxiv.org/pdf/1409.0473.pdf.［2020-05-24］.
［5］Kai Sheng Tai, Richard Socher, and Christopher D. Manning. Improved semantic representations from tree-structured long short term memory networks.［C］//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, 2015: 1556-1566.
［6］Chen H, Huang S, Chiang D, et al. Improved neural machine translation with a syntax-aware encoder and decoder［C］ //Proceedings of the 55th Annual Meetingof the Association for Computational Linguistics. Van-couver, Canada: Association for Computational Linguistics, 2017: 1936-1945.
［7］Li J, Xiong D, Tu Z, et al. Modeling source syntax for neural machine translation［C］ //Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. Vancouver, Canada: Association for Computational Linguistics, 2017: 688-697.
［8］Nguyen X,Joty S, Hoi S C, et al. Tree-structured attention with hierarchical accumulation.［EB/OL］. https://arxiv.org/pdf/2002.08046.pdf.［2020-03-14］.
［9］Sennrich R, Haddow B. Linguistic input features improve neural machine translation.［EB/OL］. https://arxiv.org/pdf/1606.02892.pdf.［2020-02-14］.
［10］Chen K, Zhao T, Yang M, et al. Translation prediction with source dependency-based context representation［C］//Proceedings of the national conference on artificial intelligence, 2017: 3166-3172
［11］Wang C, Wu S, Liu S. Source dependency-aware transformer with supervised self-attention.［EB/OL］. https://arxiv.org/pdf/1909.02273.pdf.［2019-12-14］.
［12］Ashish Vaswani, Noam Shazeer, Niki Parmar, et al. Attention is all you need［C］//Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 6000-6010.
［13］Beck D, Haffari G, Cohn T. Graph-to-Sequence learning using gated graph neural networks.［EB/OL］. https://arxiv.org/pdf/1806.09835.pdf.［2020-02-14］.
［14］Yujia Li, Daniel Tarlow, Marc Brockschmidt, et al. Gated graph sequence neural networks［C］//Proceedings of the Proceedings of ICLR, 2016: 1-20.
［15］李英, 郭剑毅, 余正涛, 等. 融合越南语语言特征与改进 PCFG 的越南语短语树库构建［J］. 南京大学学报(自然科学),2017(02): 155-165.
|
|
|
|
