none｜國立中央大學博碩士論文系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	黃嘉銘 Ka Ming, Wong
論文名稱：	A Hybrid Embedding Approach for XLM to Dialect Neural Machine Translation
指導教授：	蔡宗翰 Richard Tzong-Han Tsai
口試委員:
學位類別：	碩士 Master
系所名稱：	資訊電機學院 - 資訊工程學系 Department of Computer Science & Information Engineering
論文出版年：	2021
畢業學年度：	110
語文別：	英文
論文頁數：	35
中文關鍵詞：	無監督神經機器翻譯、深度學習、低資源
外文關鍵詞：	Unsupervised Neural Mechine Translation, Deep Learning, Low Resource
相關次數：	點閱：32 下載：0
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

粵語是漢語的變體。在中國南方地區得到廣泛應用。此外，它在世界各地有很多演講者。雖然粵語和普通話的詞系統和大部分詞義相同，但由於語法和用詞的不同，這兩種方言不能相互理解。因此，為這些語言創建翻譯模型是一項重要的工作。無監督神經機器翻譯是應用於這些語言的最理想方法，因為並行數據很少。在本文中，我們提出了一種方法，該方法結合了改進的跨語言語言模型，並對無監督神經機器翻譯進行了逐層注意。在我們的實驗中，我們觀察到我們提出的方法確實將粵語到中文和中文到粵語的翻譯提高了 1.088 和 0.394 BLEU 分數。此外，我們發現訓練數據的領域和質量對翻譯性能有巨大影響。來自社交網絡，尤其是論壇（LIHKG 連登）的粵語數據解析，不是用於方言翻譯的理想資源。

Cantonese is a variant of Chinese. It has been widely used in the southern part of China. Also, it has lots of speakers around the world. Although Cantonese and Standard Chinese share the same word system and most of the word meaning, due to the difference in grammar and use of words, these two dialects are not mutually intelligible. Therefore, creating a translation model for these languages is a significant work. Unsupervised Neural Machines Translation is the most ideal method to apply to these languages because parallel data is scarce. In this paper, we proposed a method that combined a modified cross-lingual language model and performed layer by layer attention on unsupervised neural machine translation. In our experiments, we observed that our proposed method does improve the Cantonese to Chinese and Chinese to Cantonese translation by 1.088 and 0.349 BLEU score. Also, we discovered the domain and quality of the training data has a huge impact on translation performance. Cantonese data parses from the social network, especially from forums(LIHKG 連登), is not an ideal resource to use in dialect translation.

中文摘要 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . v
Abstract . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . vi
致謝 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . vii
Contents . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ix
List of Figures . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . xi
List of Tables . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . xii
Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
Related work . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
1 Neural networks . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
1.1 Recurrent Neural Network . . . . . . . . . . . . . . . . . . . . . 5
1.2 Sequence to Sequence . . . . . . . . . . . . . . . . . . . . . . . 6
1.3 Transformer . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6
2 Pretrain Language Model . . . . . . . . . . . . . . . . . . . . . . . . . 8
2.1 BERT . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8
2.2 XLM . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8
3 Neural Machine Translation . . . . . . . . . . . . . . . . . . . . . . . . 10
3.1 Supervised Neural Machine Translation . . . . . . . . . . . . . . 10
3.2 Unsupervised Neural Machine Translation . . . . . . . . . . . . . 10
3.3 Dialect Neural Machine Translation . . . . . . . . . . . . . . . . 11
Methodology . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12
1 Purpose . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12
2 Pretrained model for Unsupervised NMT . . . . . . . . . . . . . . . . . 12
3 Modify pretrained LM . . . . . . . . . . . . . . . . . . . . . . . . . . . 13
4 Layerwise Coordination . . . . . . . . . . . . . . . . . . . . . . . . . . 15
5 Model Framework . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16
Experiment 17
1 Dataset . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17
2 Settings . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18
3 Word based vs Character based . . . . . . . . . . . . . . . . . . . . . . . 18
4 Evaluation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19
Results and Discussion 20
1 Result . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20
2 Discussion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21
2.1 Concatenation of Embeddings . . . . . . . . . . . . . . . . . . . 21
2.2 Layercoordination . . . . . . . . . . . . . . . . . . . . . . . . . 21
2.3 The increasing amount of Cantonese monolingual datasets . . . . 22
2.4 Error Cases . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25
2.5 Normalization of Words . . . . . . . . . . . . . . . . . . . . . . 26
2.6 Demonstration of the Translation Model . . . . . . . . . . . . . 29
Conclusion and Future work . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 31
1 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 31
2 Future work . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 32
Bibliography . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 33

                                

[1] Y. Wu, M. Schuster, Z. Chen, Q. V. Le, M. Norouzi, W. Macherey, M. Krikun, Y. Cao, Q. Gao, K. Macherey, J. Klingner, A. Shah, M. Johnson, X. Liu, Łukasz Kaiser, S. Gouws, Y. Kato, T. Kudo, H. Kazawa, K. Stevens, G. Kurian, N. Patil, W. Wang, C. Young, J. Smith, J. Riesa, A. Rudnick, O. Vinyals, G. Corrado, M. Hughes, and J. Dean, “Google’s neural machine translation system: Bridging the gap between human and machine translation,” 2016.
[2] Y. Wan, B. Yang, D. F. Wong, L. S. Chao, H. Du, and B. C. H. Ao, “Unsupervised neural dialect translation with commonality and diversity modeling,” 2019.
[3] T. He, X. Tan, Y. Xia, D. He, T. Qin, Z. Chen, and T.Y. Liu, “Layerwise coordination between encoder and decoder for neural machine translation,” in Advances in Neural Information Processing Systems, S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. CesaBianchi, and R. Garnett, Eds., vol. 31. Curran Associates, Inc., 2018. [Online]. Available: https://proceedings.neurips.cc/paper/2018/file/4fb8a7a22a82c80f2c26fe6c1e0dcbb3Paper.pdf
[4] I. Sutskever, O. Vinyals, and Q. V. Le, “Sequence to sequence learning with neural networks,” 2014.
[5] D. Bahdanau, K. Cho, and Y. Bengio, “Neural machine translation by jointly learning to align and translate,” 2016.
[6] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin, “Attention is all you need,” 2017.
[7] J. Devlin, M.W. Chang, K. Lee, and K. Toutanova, “Bert: Pretraining of deep bidirectional transformers for language understanding,” 2019.
[8] G. Lample and A. Conneau, “Crosslingual language model pretraining,” 2019.
[9] N. Kalchbrenner and P. Blunsom, “Recurrent continuous translation models,” in Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing. Seattle, Washington, USA: Association for Computational Linguistics, Oct. 2013, pp. 1700–1709. [Online]. Available: https://aclanthology.org/D131176
[10] M. Artetxe, G. Labaka, E. Agirre, and K. Cho, “Unsupervised neural machine translation,” 2018.
[11] G. Lample, A. Conneau, L. Denoyer, and M. Ranzato, “Unsupervised machine translation using monolingual corpora only,” 2018.
[12] R. Sennrich, B. Haddow, and A. Birch, “Improving neural machine translation models with monolingual data,” 2016.
[13] G. Lample, M. Ott, A. Conneau, L. Denoyer, and M. Ranzato, “Phrasebased & neural unsupervised machine translation,” 2018.
[14] R. Sennrich, B. Haddow, and A. Birch, “Neural machine translation of rare words with subword units,” 2016.
[15] A. Conneau, K. Khandelwal, N. Goyal, V. Chaudhary, G. Wenzek, F. Guzmán,
E. Grave, M. Ott, L. Zettlemoyer, and V. Stoyanov, “Unsupervised crosslingual representation learning at scale,” 2020.
[16] K. Papineni, S. Roukos, T. Ward, and W.J. Zhu, “Bleu: a method for automatic evaluation of machine translation,” in Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics. Philadelphia, Pennsylvania, USA: Association for Computational Linguistics, Jul. 2002, pp. 311–318. [Online]. Available: https://aclanthology.org/P02104034
[17] Y. Kim, M. Graça, and H. Ney, “When and why is unsupervised neural machine translation useless?” in Proceedings of the 22nd Annual Conference of the European Association for Machine Translation. Lisboa, Portugal: European Association for Machine Translation, Nov. 2020, pp. 35–44. [Online]. Available: https://aclanthology.org/2020.eamt1.5

簡易檢索 / 詳目顯示

相關論文