用目标语料增强机器翻译，效果媲美传统双语记忆库。
Improving Retrieval-Augmented Neural Machine Translation with Monolingual Data
- 通过源语言查询直接检索目标语言段落，融合句级与词级匹配训练。
- 在三种架构上达到与双语翻译记忆相当的性能，实测提升显著。
- 适合有大量目标语单语数据的翻译场景，尤其对真实应用有效。
传统检索增强型神经机器翻译（RANMT）系统依赖双语语料，如翻译记忆库（TMs）。但在许多场景中，目标语言的单语语料往往更易获取。本文探索如何利用此类资源：基于源语言查询，直接检索相关的目标语言片段。为此，设计了改进的跨语言检索系统，采用句级与词级匹配双重目标进行训练。在三种RANMT架构的受控实验中，该方法性能达到标准TM模型水平。此外，在真实场景下使用更大规模单语语料，相较基线和通用跨语言检索器均有显著提升。
原文摘要 · Abstract (English)
Conventional retrieval-augmented neural machine translation (RANMT) systems leverage bilingual corpora, e.g., translation memories (TMs). Yet, in many settings, monolingual corpora in the target language are often available. This work explores ways to take advantage of such resources by directly retrieving relevant target language segments, based on a source-side query. For this, we design improved cross-lingual retrieval systems, trained with both sentence level and word-level matching objectives. In our experiments with three RANMT architectures, we assess such cross-lingual objectives in a controlled setting, reaching performances that match those of standard TM-based models. We also showcase our method on a real-world settings, using much larger monolingual and observe strong improvements over both the baseline setting and general-purpose cross-lingual retrievers.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。