Boosting Factual Consistency and High Coverage in Unsupervised Abstractive Summarization

Date

2023-01-03

Contributor

Advisor

Department

Instructor

Depositor

Speaker

Researcher

Consultant

Interviewer

Narrator

Transcriber

Annotator

Journal Title

Journal ISSN

Volume Title

Publisher

Volume

Number/Issue

Starting Page

575

Ending Page

Alternative Title

Abstract

Abstractive summarization has gained attention because of the positive performance of large-scale, pretrained language models. However, models may generate a summary that contains information different from the original document. This phenomenon is particularly critical under the abstractive methods and is known as factual inconsistency. This study proposes an unsupervised abstractive method for improving factual consistency and coverage by adopting reinforcement learning. The proposed framework includes (1) a novel design to maintain factual consistency with an automatic question-answering process between the generated summary and original document, and (2) a novel method of ranking keywords based on word dependency, where keywords are used to examine the coverage of the key information preserved in the summary. The experimental results show that the proposed method outperforms the reinforcement learning baseline on both the evaluations for factual consistency and coverage.

Description

Keywords

Text Mining and Analytics, abstractive summarization, dependency, factual consistency, reinforcement learning

Citation

Extent

10

Format

Geographic Location

Time Period

Related To

Proceedings of the 56th Hawaii International Conference on System Sciences

Related To (URI)

Table of Contents

Rights

Attribution-NonCommercial-NoDerivatives 4.0 International

Rights Holder

Local Contexts

Email libraryada-l@lists.hawaii.edu if you need this content in ADA-compliant format.