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 2004.05483cs.CL
收藏

无监督的自我对话常识问答

Unsupervised Commonsense Question Answering with Self-Talk

Allen Institute for Artificial Intelligence(艾伦人工智能研究所);Paul G. Allen School of Computer Science & Engineering, University of Washington(华盛顿大学保罗·G·艾伦计算机科学与工程学院)

Vered Shwartz, Peter West, Ronan Le Bras, Chandra Bhagavatula, Yejin Choi

摘要:

自然语言理解包括用隐含的背景知识来解读字里行间的意思。当前的系统要么依赖于预先训练的语言模型作为世界知识的唯一隐式来源,要么求助于外部知识库(KB)来合并额外的相关知识。我们提出了一个基于自我对话的无监督框架,作为多项选择常识任务的新替代方案。受基于探究的发现学习(Bruner,1961)的启发,我们的方法用一些信息寻求问题(如“$\textit{what is the definition of ...}$“)来查询语言模型,以发现额外的背景知识。实证结果表明,自我对话过程大大提高了性能的zero-shot语言模型基线上的四个常识基准,并与模型,从外部知识库获取知识。虽然我们的方法在几个基准测试中提高了性能,但即使在导致正确答案的情况下,自我对话诱导的知识也并不总是被人类判断者视为有用的,这就提出了关于常识推理的预训练语言模型的内部工作原理的有趣问题。

英文摘要:

Natural language understanding involves reading between the lines with implicit background knowledge. Current systems either rely on pre-trained language models as the sole implicit source of world knowledge, or resort to external knowledge bases (KBs) to incorporate additional relevant knowledge. We propose an unsupervised framework based on self-talk as a novel alternative to multiple-choice commonsense tasks. Inspired by inquiry-based discovery learning (Bruner, 1961), our approach inquires language models with a number of information seeking questions such as "$\textit{what is the definition of ...}$" to discover additional background knowledge. Empirical results demonstrate that the self-talk procedure substantially improves the performance of zero-shot language model baselines on four out of six commonsense benchmarks, and competes with models that obtain knowledge from external KBs. While our approach improves performance on several benchmarks, the self-talk induced knowledge even when leading to correct answers is not always seen as useful by human judges, raising interesting questions about the inner-workings of pre-trained language models for commonsense reasoning.

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。

↑