Tibetan-Chinese Bidirectional Machine Translation Based on VOLT

Abstract

Abstract: The generation of Tibetan-Chinese vocabulary is not only the first step of Tibetan-Chinese bi-directional machine translation task, but also affects the performance of Tibetan-Chinese bi-directional machine translation. This paper improves the performance of downstream Tibetan-Chinese bidirectional translation by improving the generation of Tibetan-Chinese word lists. On the one hand, it starts with word list splicing, using normal word lists for high frequencies and byte pair encoding word lists for low frequencies, and finding the optimal word frequency threshold through iterative training; On the other hand, according to the optimal transport theory proposed by vocabulary learning approach, the Tibetan-Chinese vocabulary is generated, which is improved according to the characteristics of Tibetan language and applied to Tibetan-Chinese bidirectional translation. The experimental results show that, it is demonstrated that the byte pair encoding plus optimal transmission lexical learning method proposed in this paper for Tibetan language characteristics works best, reaching a BLEU value of 37.35 for the Tibetan-Chinese translation task and 27.60 for the Chinese-Tibetan translation task.

Key words: Tibetan word list, byte pair encoding, two-way Tibetan-Chinese translation, VOLT

SUN Yi-dong, YONG Cuo, YANG Dan, . Tibetan-Chinese Bidirectional Machine Translation Based on VOLT[J]. Computer and Modernization, 2022, 0(05): 28-32.

References ［28］

［1］	李沐,刘树杰,张冬冬,等. 机器翻译［M］. 北京:高等教育出版社, 2018.
［2］	NAGAO M. A framework of a mechanical translation between Japanese and English by analogy principle［C］// Proceedings of the International NATO Symposium on Artificial and Human Intelligence. 1984:173-180.
［3］	BROWN P F, COCKE J, PIETRA S A D, et al. A statistical approach to machine translation［J］. Computational Linguistics, 2002,16(2):79-87.
［4］	BROWN P F, DELLA PIETRA S A, DELLA PIETRA V J, et al. The mathematics of statistical machine translation: Parameter estimation［J］. Computational Linguistics, 1993,19(2):263-311.
［5］	KOEHN P, OCH F J, MARCU D. Statistical phrase-based translation［C］// Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology. 2003:48-54.
［6］	BAHDANAU D, CHO K, BENGIO Y. Neural machine translation by jointly learning to align and translate［J］. arXiv preprint arXiv:1409.0473, 2016.
［7］	SUTSKEVER I, VINYALS O, LE Q V. Sequence to sequence learning with neural networks［C］// Advances in Neural Information Processing Systems. 2014:3104-3112.
［8］	冯洋,邵晨泽. 神经机器翻译前沿综述［J］. 中文信息学报, 2020,34(7):1-18.
［9］	李亚超,熊德意,张民. 神经机器翻译综述［J］. 计算机学报, 2018,41(12):2734-2755.
［10］	肖桐,朱靖波. 机器翻译: 基础与模型［M］. 北京:电子工业出版社, 2021.
［11］	GARCIA-MARTINEZ M, BARRAULT L, BOUGARES F. Factored neural machine translation architectures［C］// International Workshop on Spoken Language Translation (IWSLT’16). 2016.
［12］	JEAN S, CHO K, MEMISEVIC R, et al. On using very large target vocabulary for neural machine translation［J］. arXiv preprint arXiv:1412.2007, 2014.
［13］	SENNRICH R, HADDOW B, BIRCHA. Neural machine translation of rare words with subword units ［C］// Proceedings of ACL. 2016.DOI: 10.48550/arXiv.1508.07909
［14］	KUDO T. Subword regularization: Improving neural network translation models with multiple subword candidates［J］. arXiv preprint arXiv:1804.10959, 2018.
［15］	GAGE P. A new algorithm for data compression［J］. C Users Journal, 1994,12(2):23-38.
［16］	WANG C H, CHO K Y, GU J T. Neural machine translation with byte-level subwords［C］// Proceedings of the AAAI Conference on Artificial Intelligence. 2020:9154-9160.
［17］	SCHUSTER M, NAKAJIMA K. Japanese and Korean voice search［C］// 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 2012:5149-5152.
［18］	KUDO T. Subword regularization: Improving neural network translation models with multiple subword candidates［C］// Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics. 2018. DOI: 10.18653/v1/P18-1007.
［19］	薛明亚,余正涛,文永华,等. 融合EMD最小化双语词典的汉—越无监督神经机器翻译［J］. 中文信息学报, 2021,35(3):43-50.
［20］	XU J J, ZHOU H, GAN C, et al. Vocabulary learning via optimal transport for neural machine translation［C］// Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing. 2021. DOI: 10.18653/v1/2021.acl-long.571
［21］	沙九,冯冲,张天夫,等. 多策略切分粒度的藏汉双向神经机器翻译研究［J］. 厦门大学学报(自然科学版), 2020,59(2):213-219.
［22］	WEI J, ZOU K. EDA: Easy data augmentation techniques for boosting performance on text classification tasks［J］. arXiv preprint arXiv:1901.11196, 2019.
［23］	LUO R X, XU J J, ZHANG Y, et al. PKUSEG: A toolkit for multi-domain chinese word segmentation［J］. arXiv preprint arXiv:1906.11455, 2019.
［24］	李亚超,江静,加羊吉,等. TIP-LAS: 一个开源的藏文分词词性标注系统［J］. 中文信息学报, 2015,29(6):203-207.
［25］	VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need［C］// Proceedings of the 31st Conference on Neural Information Processing Systems. 2017:6000-6010.
［26］	WISEMAN S, RUSH A M. Sequence-to-sequence learning as beam-search optimization［C］// Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. 2016. DOI: 10.18653/v1/D16-1137.
［27］	KLEIN G, KIM Y, DENGY, et al. OpenNMT: Open-source toolkit for neural machine translation［C］// Proceedings of ACL, System-Demonstrations. 2017:67-72.
［28］	PAPINENI K, ROUKOS S, WARD T, et al. BLEU: A method for automatic evaluation of machine translation［C］// Proceedings of ACL. 2002:311-318.

[1]	PENG Sui, XU Liang, ZHANG Zhi-qiang, LOU Yuan-yuan, YU Hao, QIN Xiao-hui. Probabilistic Voltage Stability Evaluation Algorithm Based on Mixed Vine Copula and ILHS [J]. Computer and Modernization, 2022, 0(12): 6-12.
[2]	GUO Teng-fei, ZHANG Ze-yan, FU Hong-cai, WANG Ji-xuan, NIU Tian-bao. Lightweight Infrared HV Bushing Identification Algorithm Based on Attention Mechanism [J]. Computer and Modernization, 2022, 0(01): 70-76.
[3]	LI Yan-sheng. Load Forecasting Method of Distribution Network Based on Neural Network [J]. Computer and Modernization, 2021, 0(06): 69-73.
[4]	SONG Liang-cai, SUO Gui-long, HU Jun-tao, DOU Yan-mei, CUI Zhi-yong. Encoder-Decoder Photovoltaic Power Generation Prediction#br# Model Based on Attention Mechanism#br# [J]. Computer and Modernization, 2020, 0(09): 112-117.
[5]	SHAO Xin-tian， LI Zhi-hua， WANG Zhen. Analog Circuit Fault Diagnosis Based on Modified Fruit Fly Optimization Algorithm [J]. Computer and Modernization, 2018, 0(01): 40-43.
[6]	ZHENG Bo-chuan. A Lotka-Volterra Recurrent Neural Network Model for Solving TSP [J]. Computer and Modernization, 2013, 1(8): 204-208.
[7]	LI Feng;LIU Chun-sheng;XU Xiao-chun. Improved Composite Algorithm in Photovoltaic Generation System [J]. Computer and Modernization, 2013, 1(8): 57-59.
[8]	CAO Qian;ZHAO Jia-bao;YU Qing-rong. Research and Design of Intelligent Monitoring System of Photovoltaic Equipment Based on CAN [J]. Computer and Modernization, 2013, 1(3): 148-151.
[9]	LI Wen-jie;SUN Zhi-yi;HE Qiu-sheng. Study on SPLL of Grid-connected PV Generation System [J]. Computer and Modernization, 2012, 1(9): 54-56,6.
[10]	LIU Quan-qiang;LIU Jing-hao;LIU Fei. Design of Signal Transmission System Based on Power Line [J]. Computer and Modernization, 2012, 1(1): 111-114,.
[11]	LI Jianjun;ZUO Wei. Research of Torque of Stepping Motor Driver Based on Switching [J]. Computer and Modernization, 2012, 1(03): 155-158.
[12]	ZHU Yu-yuan;TU Ping . Design and Analysis of Network Voltage Monitor System [J]. Computer and Modernization, 2011, 1(6): 108-4.
[13]	LIU Xiao-jie;SUN Pei-de;TU Li-jun. A New Single-phase Shunt Active Power Filter [J]. Computer and Modernization, 2010, 1(4): 0-199.