提出在翻译后处理阶段做同音字归一化，避免训练数据失真。
A Case Against Implicit Standards: Homophone Normalization in Machine Translation for Languages that use the Ge'ez Script
- 将同音字归一化从训练阶段移到推理后处理。
- 在阿姆哈拉语翻译中提升1.03的BLEU分数。
- 适合关注语言多样性和模型泛化的研究者。
同音字归一化（将发音相同但书写不同的字符映射为同一字符）是阿姆哈拉语自然语言处理中的预处理步骤。尽管这能提高自动评估指标的表现，却导致模型无法理解同一语言的不同书写形式，且可能影响跨语言迁移性能。本文通过单语训练与跨语言迁移实验，探究归一化对使用格埃兹字母语言的影响，并提出一种后推理干预策略：仅在模型输出时进行归一化，而非训练数据。该方法在保持训练数据语言特征的同时，使BLEU分数最高提升1.03。研究呼吁更注重语言本体差异的技术干预，推动技术驱动的语言演变讨论。
原文摘要 · Abstract (English)
Homophone normalization, where characters that have the same sound in a writing script are mapped to one character, is a pre-processing step applied in Amharic Natural Language Processing (NLP) literature. While this may improve performance reported by automatic metrics, it also results in models that are not able to understand different forms of writing in a single language. Further, there might be impacts in transfer learning, where models trained on normalized data do not generalize well to other languages. In this paper, we experiment with monolingual training and cross-lingual transfer to understand the impacts of normalization on languages that use the Ge'ez script. We then propose a post-inference intervention in which normalization is applied to model predictions instead of training data. With our simple scheme of post-inference normalization, we show that we can achieve an increase in BLEU score of up to 1.03 while preserving language features in training. Our work contributes to the broader discussion on technology-facilitated language change and calls for more language-aware interventions.
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。