arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1912.00567cs.CL
收藏

将外部双语对融合到神经机器翻译中

Merging External Bilingual Pairs into Neural Machine Translation

Soochow University(苏州大学);University of Lisbon(里斯本大学)

Tao Wang, Shaohui Kuang, Deyi Xiong, António Branco

摘要:

由于神经机器翻译(NMT)不容易明确纠正错误,因此将预先指定的翻译合并到NMT中被广泛认为是一个不平凡的挑战。在本文中,我们提出并探讨了三种方法来赋予NMT与预先指定的双语对。例如,在解码过程中修改束搜索算法或对注意力机制进行复杂的修改-解决这一挑战的主流方法-,我们对训练数据进行了适当的预处理,以添加有关预先指定的翻译的信息。额外的嵌入也用于区分预先指定的令牌和其他令牌。大量的实验和分析表明,超过99%的预先指定的短语被成功翻译(给定85%的基线),并且使用本文探讨的方法,翻译质量也有实质性的提高。

英文摘要:

As neural machine translation (NMT) is not easily amenable to explicit correction of errors, incorporating pre-specified translations into NMT is widely regarded as a non-trivial challenge. In this paper, we propose and explore three methods to endow NMT with pre-specified bilingual pairs. Instead, for instance, of modifying the beam search algorithm during decoding or making complex modifications to the attention mechanism --- mainstream approaches to tackling this challenge ---, we experiment with the training data being appropriately pre-processed to add information about pre-specified translations. Extra embeddings are also used to distinguish pre-specified tokens from the other tokens. Extensive experimentation and analysis indicate that over 99% of the pre-specified phrases are successfully translated (given a 85% baseline) and that there is also a substantive improvement in translation quality with the methods explored here.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑