探究词汇重叠对多语言翻译知识迁移的影响，发现语言相关性比共享词表更重要。
The Impact of Vocabulary Overlaps on Knowledge Transfer in Multilingual Machine Translation
- 对比共享与非共享词表，设计跨领域迁移实验
- 语言相关性和领域匹配比词汇重叠更能提升性能
- 适用于研究多语言模型知识迁移机制的学者
知识迁移在相关语言间的多语言神经机器翻译（MNMT）中被证实有益，但某些方面仍缺乏深入研究。通常采用联合词表构建统一的词嵌入空间，然而非共享词表对模型性能的影响却未得到充分探讨，因此尚无共识认为知识迁移主要源于词汇重叠。本文通过系统实验对比联合与非共享词表，并引入与源语言相关和不相关的辅助语言，在跨领域设置下强调知识迁移及辅助语言的影响。结果表明，尽管相关语言具有更广泛的词汇重叠时表现更好，但语言相关性和领域匹配的重要性超过联合词表。
原文摘要 · Abstract (English)
Knowledge transfer, especially across related languages, has been found beneficial for multilingual neural machine translation (MNMT), but some aspects are still under-explored and deserve further investigation. A joint vocabulary is most often applied to form a uniform word embedding space, but since the impact of a disjoint vocabulary on model performance is far less studied, there is no consensus on how much knowledge transfer is mainly due to vocabulary overlap. In this paper, we present systematic experiments with joint and disjoint vocabularies, and auxiliary languages related and unrelated to the source language. We design this experiment in an out-of-domain setup in order to emphasize transfer and the impact of the auxiliary language. As expected, we yield better results with more extensive vocabulary overlaps typical for related languages, but our experiments also show that domain-match and language relatedness are more important than a joint vocabulary.
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。