扩充WMT24++基准,新增六种罗曼什语方言数据集。
Expanding the WMT24++ Benchmark with Rumantsch Grischun, Sursilvan, Sutsilvan, Surmiran, Puter, and Vallader
- 构建六种罗曼什语方言的平行语料库,基于WMT24++标准
- 机器翻译系统对罗曼什语转德语表现较好,但反向翻译仍困难
- 为瑞士罗曼什语提供首个跨方言评估基准,适合语言资源研究者
罗曼什语是瑞士的本土语言,其机器翻译评估资源有限。本文构建了六种罗曼什语变体的评测基准,包括一种超区域通用变体Rumantsch Grischun及五种地区变体:Sursilvan、Sutsilvan、Surmiran、Puter和Vallader。参考译文由人工翻译生成,与超过55种语言保持并行性,基于WMT24++基准。自动评估显示,所有变体中从罗曼什语到德语的翻译表现相对良好,但反向翻译(德语到罗曼什语)仍具挑战性。
原文摘要 · Abstract (English)
The Romansh language, spoken in Switzerland, has limited resources for machine translation evaluation. In this paper, we present a benchmark for six varieties of Romansh: Rumantsch Grischun, a supra-regional variety, and five regional varieties: Sursilvan, Sutsilvan, Surmiran, Puter, and Vallader. Our reference translations were created by human translators based on the WMT24++ benchmark, which ensures parallelism with more than 55 other languages. An automatic evaluation of existing MT systems and LLMs shows that translation out of Romansh into German is handled relatively well for all the varieties, but translation into Romansh is still challenging.
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。