arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2311.16865cs.CL
收藏

一种用于评估无标准正字法方言机器翻译指标性能的基准

A Benchmark for Evaluating Machine Translation Metrics on Dialects Without Standard Orthography

University of Zurich(苏黎世大学);Textshuttle(Textshuttle公司);ETH Zurich(苏黎世联邦理工学院);University of Edinburgh(爱丁堡大学)

Noëmi Aepli, Chantal Amrhein, Florian Schottmann, Rico Sennrich

AI总结:

本文构建了首个针对无标准正字法方言的机器翻译评估基准,通过收集瑞士德语方言的人工翻译与判断数据并建立挑战集,揭示了现有指标在片段级别评估上的不可靠性,并提出了初步的鲁棒性改进设计。

摘要:

为了在自然语言处理领域取得合理进展,我们必须意识到所使用评估指标的局限性。在本研究中,我们评估了现有指标对非标准化方言的鲁棒性,即没有标准正字法的语言变体中存在的拼写差异。为此,我们收集了一个数据集,包含从英语到两种瑞士德语方言的自动机器翻译的人工翻译和人工判断。我们进一步创建了一个针对方言变体的挑战集,并对现有指标的性能进行了基准测试。我们的结果表明,现有指标无法可靠地评估瑞士德语的文本生成输出,尤其是在片段级别上。我们提出了初步的设计调整方案,以提高在面对非标准化方言时的鲁棒性,尽管仍有很大的改进空间。数据集、代码和模型可在此处获取:https://github.com/textshuttle/dialect_eval

英文摘要:

For sensible progress in natural language processing, it is important that we are aware of the limitations of the evaluation metrics we use. In this work, we evaluate how robust metrics are to non-standardized dialects, i.e. spelling differences in language varieties that do not have a standard orthography. To investigate this, we collect a dataset of human translations and human judgments for automatic machine translations from English to two Swiss German dialects. We further create a challenge set for dialect variation and benchmark existing metrics' performances. Our results show that existing metrics cannot reliably evaluate Swiss German text generation outputs, especially on segment level. We propose initial design adaptations that increase robustness in the face of non-standardized dialects, although there remains much room for further improvement. The dataset, code, and models are available here: https://github.com/textshuttle/dialect_eval

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。

↑