机器翻译、变音符号与变音符号恢复之间的相互作用
Interplay of Machine Translation, Diacritics, and Diacritization
AI总结：
该研究在 55 种非洲及欧洲语言上考察机器翻译与变音符号恢复的多任务相互作用及变音符号保留与否的影响，并提出与模型性能正相关的变音系统复杂度指标。
摘要：
我们研究了两个研究问题：（1）在多任务学习环境中，机器翻译（MT）和变音符号恢复如何相互影响彼此的性能；（2）保留（相较于移除）变音符号对 MT 性能的影响。我们在高资源（HR）和低资源（LR）两种设置下，跨 55 种不同语言（36 种非洲语言和 19 种欧洲语言）考察了这两个问题。对于问题（1），结果表明，变音符号恢复在 LR 场景中显著有利于 MT，使某些语言的性能提升一倍甚至两倍，但在 HR 场景中会损害 MT。我们发现，在 LR 场景中 MT 会损害变音符号恢复，但在 HR 场景中对某些语言的变音符号恢复有显著助益。对于问题（2），无论保留还是移除变音符号，MT 性能都相近。此外，我们提出了两类用于衡量变音符号系统复杂度的指标，并发现这些指标与我们的变音符号恢复模型的性能呈正相关。总体而言，我们的工作为在不同数据规模条件下开发 MT 和变音符号恢复系统提供了洞见，并可能产生可推广到我们所研究的 55 种语言之外的影响。
英文摘要：
We investigate two research questions: (1) how do machine translation (MT) and diacritization influence the performance of each other in a multi-task learning setting (2) the effect of keeping (vs. removing) diacritics on MT performance. We examine these two questions in both high-resource (HR) and low-resource (LR) settings across 55 different languages (36 African languages and 19 European languages). For (1), results show that diacritization significantly benefits MT in the LR scenario, doubling or even tripling performance for some languages, but harms MT in the HR scenario. We find that MT harms diacritization in LR but benefits significantly in HR for some languages. For (2), MT performance is similar regardless of diacritics being kept or removed. In addition, we propose two classes of metrics to measure the complexity of a diacritical system, finding these metrics to correlate positively with the performance of our diacritization models. Overall, our work provides insights for developing MT and diacritization systems under different data size conditions and may have implications that generalize beyond the 55 languages we investigate.
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。
