arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.06342cs.CL
收藏

在上下文感知神经机器翻译中促进目标数据的作用

Promoting Target Data in Context-aware Neural Machine Translation

Vicomtech Foundation(维康泰克基金会);Basque Research and Technology Alliance (BRTA)(巴斯克研究与技术联盟(BRTA));University of the Basque Country UPV/EHU(巴斯克大学(UPV/EHU))

Harritxu Gete, Thierry Etchegoyhen

AI总结:

本研究探讨在拼接式上下文感知NMT中增强目标上下文的策略,实验证明将目标上下文并入源端可显著提升目标语言现象翻译质量,且结合双上下文效果最佳。

摘要:

标准上下文感知神经机器翻译(NMT)通常依赖平行文档级数据,同时利用源语言和目标语言的上下文。特别是基于拼接的方法,仍然是文档级NMT的强基线,它将源语言和/或目标语言的上下文句子前置到待翻译句子之前,其中在每一侧利用相等数量的源语言和目标语言数据的模型变体达到了最先进的结果。在这项工作中,我们研究在标准拼接方法中是否应进一步促进目标数据的作用,因为大多数文档级现象依赖于目标语言侧存在的信息。我们评估了新颖的基于拼接的变体,其中目标语言上下文被前置到源语言中,无论是单独使用还是与源语言上下文结合使用。在英语-俄语和巴斯克语-西班牙语的实验结果表明,将目标语言上下文包含在源语言中能大幅改善目标语言现象。在依赖源语言的现象上,仅在源语言中使用目标语言上下文与最先进的拼接方法达到同等水平,或略逊一筹,而在源语言侧结合源语言和目标语言上下文则全面带来显著提升。

英文摘要:

Standard context-aware neural machine translation (NMT) typically relies on parallel document-level data, exploiting both source and target contexts. Concatenation-based approaches in particular, still a strong baseline for document-level NMT, prepend source and/or target context sentences to the sentences to be translated, with model variants that exploit equal amounts of source and target data on each side achieving state-of-the-art results. In this work, we investigate whether target data should be further promoted within standard concatenation-based approaches, as most document-level phenomena rely on information that is present on the target language side. We evaluate novel concatenation-based variants where the target context is prepended to the source language, either in isolation or in combination with the source context. Experimental results in English-Russian and Basque-Spanish show that including target context in the source leads to large improvements on target language phenomena. On source-dependent phenomena, using only target language context in the source achieves parity with state-of-the-art concatenation approaches, or slightly underperforms, whereas combining source and target context on the source side leads to significant gains across the board.

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。

↑