用印地语作桥梁，提升尼泊尔语到英语的低资源翻译效果
Pivot Language for Low-Resource Machine Translation
- 以印地语为中间语言，结合监督与半监督方法进行翻译
- 在开发集上达到14.2的SacreBLEU分，较基线提升6.6分
- 适合研究低资源语言对翻译及跨语言迁移的学者
某些语言对因缺乏大规模、多领域平行语料而面临翻译困难。本文采用印地语作为桥梁语言，实现尼泊尔语到英语的翻译。我们分析了印地语作为枢纽语言的优势，并对比了两种应用方式：完全监督的迁移法和半监督的反向翻译法。使用迁移法，我们在开发集上获得14.2的SacreBLEU分数，比Guzman等人（2019）报告的全监督基线分高6.6分。虽然略低于半监督基线的15.1分，但文中讨论了可能原因并指出了未来改进方向。
原文摘要 · Abstract (English)
Certain pairs of languages suffer from lack of a parallel corpus which is large in size and diverse in domain. One of the ways this is overcome is via use of a pivot language. In this paper we use Hindi as a pivot language to translate Nepali into English. We describe what makes Hindi a good candidate for the pivot. We discuss ways in which a pivot language can be used, and use two such approaches - the Transfer Method (fully supervised) and Backtranslation (semi-supervised) - to translate Nepali into English. Using the former, we are able to achieve a devtest Set SacreBLEU score of 14.2, which improves the baseline fully supervised score reported by (Guzman et al., 2019) by 6.6 points. While we are slightly below the semi-supervised baseline score of 15.1, we discuss what may have caused this under-performance, and suggest scope for future work.
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。