arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2305.13751cs.CL
收藏

上下文感知神经机器翻译中的挑战

Challenges in Context-Aware Neural Machine Translation

Information Sciences Institute(信息科学研究所);University of Southern California(南加州大学);University of Washington(华盛顿大学)

Linghao Jin, Jacqueline He, Jonathan May, Xuezhe Ma

AI总结:

本文调查了上下文感知神经机器翻译在话语现象、上下文使用、模型架构和评估方面的挑战,并提出段落到段落翻译设置及中英文小说数据集以促进未来研究。

摘要:

上下文感知神经机器翻译利用句子级上下文之外的信息来解决句间话语依赖关系,并提升文档级翻译质量,近期涌现了多种技术。然而,尽管有合理的直觉,大多数上下文感知翻译模型相比句子级系统仅表现出适度的提升。在本研究中,我们调查了阻碍该领域发展的几个挑战,涉及话语现象、上下文使用、模型架构和文档级评估。为解决这些问题,我们提出了一种更现实的文档级翻译设置,称为段落到段落(para2para)翻译,并收集了一个新的中英文小说数据集以促进未来研究。

英文摘要:

Context-aware neural machine translation involves leveraging information beyond sentence-level context to resolve inter-sentential discourse dependencies and improve document-level translation quality, and has given rise to a number of recent techniques. However, despite well-reasoned intuitions, most context-aware translation models show only modest improvements over sentence-level systems. In this work, we investigate several challenges that impede progress within this field, relating to discourse phenomena, context usage, model architectures, and document-level evaluation. To address these problems, we propose a more realistic setting for document-level translation, called paragraph-to-paragraph (para2para) translation, and collect a new dataset of Chinese-English novels to promote future research.

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。

↑