Reinforced Extractive Summarization With Question-Focused Rewards

Abstract

We investigate a new training paradigm for extractive summarization. Traditionally, human abstracts are used to derive goldstandard labels for extraction units. However, the labels are often inaccurate, because human abstracts and source documents cannot be easily aligned at the word level. In this paper we convert human abstracts to a set of Cloze-style comprehension questions. System summaries are encouraged to preserve salient source content useful for answering questions and share common words with the abstracts. We use reinforcement learning to explore the space of possible extractive summaries and introduce a question-focused reward function to promote concise, fluent, and informative summaries. Our experiments show that the proposed method is effective. It surpasses state-of-the-art systems on the standard summarization dataset.

Publication Date

1-1-2018

Publication Title

ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Student Research Workshop

Number of Pages

105-111

Document Type

Article; Proceedings Paper

Personal Identifier

scopus

DOI Link

https://doi.org/10.18653/v1/p18-3015

Socpus ID

85063108636 (Scopus)

Source API URL

https://api.elsevier.com/content/abstract/scopus_id/85063108636

This document is currently not available here.

Share

COinS