Summarize-then-Answer: Generating Concise Explanations for Multi-hop Reading Comprehension
Summarize-then-Answer: Generating Concise Explanations for Multi-hop Reading Comprehension
复制标题
DOI：
10.18653/v1/2021.emnlp-main.490
复制
发表时间：
2021-09
期刊：
影响因子：
--
通讯作者：
Naoya Inoue;H. Trivedi;Steven K. Sinha;Niranjan Balasubramanian;Kentaro Inui
中科院分区：
文献类型：
--
作者：
Naoya Inoue;H. Trivedi;Steven K. Sinha;Niranjan Balasubramanian;Kentaro Inui
我们如何为多跳阅读理解（RC）生成简明的解释？目前的支持句识别策略可以看作是对输入文本的一种抽取式的以问题为中心的摘要。然而，这些抽象的解释不一定是简洁的，即不足以回答一个问题。相反，我们提倡一种抽象的方法，我们建议生成一个以问题为中心的，抽象的输入段落摘要，然后将其馈送到RC系统。给定有限数量的人类注释的抽象解释，我们以半监督的方式训练抽象解释器，我们从监督模型开始，然后通过试错来进一步训练它，最大化简洁性促进的奖励函数。我们的实验表明，建议的抽象解释器可以产生更紧凑的解释比一个提取的解释器有限的监督（只有2k个实例），同时保持足够的。
How can we generate concise explanations for multi-hop Reading Comprehension (RC)? The current strategies of identifying supporting sentences can be seen as an extractive question-focused summarization of the input text. However, these extractive explanations are not necessarily concise i.e. not minimally sufficient for answering a question. Instead, we advocate for an abstractive approach, where we propose to generate a question-focused, abstractive summary of input paragraphs and then feed it to an RC system. Given a limited amount of human-annotated abstractive explanations, we train the abstractive explainer in a semi-supervised manner, where we start from the supervised model and then train it further through trial and error maximizing a conciseness-promoted reward function. Our experiments demonstrate that the proposed abstractive explainer can generate more compact explanations than an extractive explainer with limited supervision (only 2k instances) while maintaining sufficiency.