会议场景下通过语音识别和机器翻译技术实现从演讲人语音到另外一种语言文字的翻译,对于跨语言信息交流具有重要意义,成为当前研究热点之一。该文针对由于会议行业属性带来的专业术语和行业用语的翻译问题,提出了一种融合外部词典知识的领域个性化方法。具体而言,首先采用联合占位符和拼接融合的编码策略,通过引入外部词典知识,在提升实体词、专业术语词翻译准确率的同时,兼顾翻译结果的流畅性。其次提出基于分类的领域旁支参数个性化自适应策略,在保持通用领域翻译效果的情况下实现会议相关领域翻译质量的提升。最后基于上述方案,设计了一套领域个性化自动训练系统。实验结果表明,在中英体育、商务和医学会议翻译任务上,该系统在不影响通用翻译的情况下,平均提升9.22个BLEU,获得较好翻译效果。
Abstract
Translation of a presenter's speech into other languages through speech recognition and machine translation in conference scenario is of great significance for cross-language communication. This paper proposes a domain-specific machine translation method based on external dictionary knowledge, so as to handle the translation of terminologies and professional expressions for a given conference. First, a constructed external dictionary is integrated through combining placeholder and concatenation fusion methods. The translation quality of domain related entity words and terminologies is significantly improved while maintaining coherence and fluency of the context. Second, classification-based domain adaptation can further improve the translation of the speech for a given conference while maintaining the overall quality of the general domain translation. Finally, an automatic domain adaptation training system is designed based on the above methods. The experimental results on Chinese to English translation task indicate that the proposed system achieves 9.22 BLEU improvement in average for sports, business and medical conference, without afftecting the general translation quality.
关键词
机器翻译 /
词典知识 /
领域个性化
{{custom_keyword}} /
Key words
machine translation /
dictionary knowledge /
domain customization
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Takezawa T, Sumita E, Sugaya F, et al. Toward a broad-coverage bilingual corpus for speech translation of travel conversations in the real world[C]//Proceedings of LREC, 2002:147-152.
[2] Jan N, Cattoni R, Sebastian S, et al. The IWSLT 2018 evaluation campaign[C]//Proceedings of International Workshop on Spoken Language Translation, 2018:2-6.
[3] Sutskever I, Vinyals O, Le Q V. Sequence to sequence learning with neural networks[C]//Proceedings of Advances in Neural Information Processing Systems, 2014:3104-3112.
[4] Bahdanau D, Cho K, Bengio Y. Neural machine translation by jointly learning to align and translate[J]. arXiv preprint arXiv: 1409.0473, 2014.
[5] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[C]//Proceedings of Advances in Neural Information Processing Systems. 2017:5998-6008.
[6] Hokamp C, Liu Q. Lexically constrained decoding for sequence generation using grid beam search[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, 2017,1:1535-1546.
[7] Feng Y, Zhang S, Zhang A, et al. Memory-augmented neural machine translation[C]//Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, 2017:1390-1399.
[8] Pham N Q, Niehues J, Waibel A. Towards one-shot learning for rare-word translation with external experts[C]//Proceedings of the 2nd Workshop on Neural Machine Translation and Generation, 2018:100-109.
[9] Luong M T, Manning C D. Stanford neural machine translation systems for spoken language domains[C]//Proceedings of the International Workshop on Spoken Language Translation, 2015:76-79.
[10] Britz D, Le Q, Pryzant R. Effective domain mixing for neural machine translation[C]//Proceedings of the 2nd Conference on Machine Translation, 2017:118-126.
[11] Crego J, Kim J, Klein G, et al. Systran's pure neural machine translation systems[J]. arXiv preprint arXiv: 1610.05540, 2016.
[12] Gu J, Lu Z, Li H, et al. Incorporating copying mechanism in sequence-to-sequence learning[J]. arXiv preprint arXiv: 1603.06393, 2016.
[13] Vinyals, Fortunato M, Jaitly N. Pointer networks[C]//Proceedings of Advances in Neural Information Processing Systems, 2015:2692-2700.
[14] Chu C, Wang R. A survey of domain adaptation for neural machine translation[C]//Proceedings of the 27th International Conference on Computational Linguistics 2018:1304-1319.
[15] Lecun Y, Bengio Y. Convolutional networks for images, speech, and time series[M]. The handbook of brain theory and neural networks. MIT Press, 1998.
[16] Rupesh Kumar Srivastava, Klaus Greff, Jurgen Schmidhuber. Highway networks[C]//Proceedings of Presented at the Deep Learning Workshop, International Conference on Machine Learning, Lille, France, 2015.
[17] Rico Sennrich, Barry Haddow, Alexandra Birch. Improving neural machine translation models with monolingual data[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. Berlin, Germany. Association for Computational Linguistics, 2016:86-96.
[18] Fadaee M, Monz C. Back-translation sampling by targeting difficult words in neural machine translation[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Belgium, 2018:435-446.
[19] R Sennrich, B Haddow, A Birch. Neural machine translation of rare words with subword units[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. Berlin, Germany, 2016.
[20] Papineni K, Roukos S, Ward T, et al. BLEU: A method for automatic evaluation of machine translation[C]// Proceedings of the 40th Annual Meeting on Association for Computational Linguistics. Association for Computational Linguistics, 2002:311-318.
[21] Guillaume Lample, Miguel Ballesteros, Sandeep Subramanian, et al. Neural architectures for named entity recognition[C]//Proceedings of NAACL, 2016.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
PDF(1946 KB)
