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 2104.02115cs.CLcs.AI
收藏

用于自然语言理解的离散推理模板

Discrete Reasoning Templates for Natural Language Understanding

Imperial College London(帝国理工学院)

Hadeel Al-Negheimish, Pranava Madhyastha, Alessandra Russo

摘要:

从文章的多个部分中推理信息以得出答案是对阅读理解模型的一个公开挑战。在本文中,我们提出了一种方法,原因复杂的问题,将其分解为更简单的子问题,可以利用单跨度提取阅读理解模型,并得出最终的答案,根据指令在一个预定义的推理模板。我们专注于基于减法的算术问题,并评估我们的方法的DROP数据集的一个子集。我们表明,我们的方法是有竞争力的国家的最先进的,而被解释,并要求很少的监督

英文摘要:

Reasoning about information from multiple parts of a passage to derive an answer is an open challenge for reading-comprehension models. In this paper, we present an approach that reasons about complex questions by decomposing them to simpler subquestions that can take advantage of single-span extraction reading-comprehension models, and derives the final answer according to instructions in a predefined reasoning template. We focus on subtraction-based arithmetic questions and evaluate our approach on a subset of the DROP dataset. We show that our approach is competitive with the state-of-the-art while being interpretable and requires little supervision

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。

↑