arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.03392cs.CL
收藏

自然语言推理中不一致原因的调查

Investigating Reasons for Disagreement in Natural Language Inference

The Ohio State University(俄亥俄州立大学);UCLouvain(鲁汶大学)

Nan-Jiang Jiang, Marie-Catherine de Marneffe

摘要:

我们研究如何在自然语言推理(NLI)注释出现分歧。我们开发了一个分类法的分歧来源,10个类别跨越3个高级别的类。我们发现,一些分歧是由于句子意义的不确定性,其他注释者的偏见和任务工件,导致不同的解释的标签分布。我们探讨了两种建模方法来检测项目与潜在的分歧:4路分类与“复杂”的标签,除了三个标准的NLI标签,和多标签分类方法。我们发现,多标签分类是更有表现力,并给出了更好的回忆数据中可能的解释。

英文摘要:

We investigate how disagreement in natural language inference (NLI) annotation arises. We developed a taxonomy of disagreement sources with 10 categories spanning 3 high-level classes. We found that some disagreements are due to uncertainty in the sentence meaning, others to annotator biases and task artifacts, leading to different interpretations of the label distribution. We explore two modeling approaches for detecting items with potential disagreement: a 4-way classification with a "Complicated" label in addition to the three standard NLI labels, and a multilabel classification approach. We found that the multilabel classification is more expressive and gives better recall of the possible interpretations in the data.

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。

↑