Discourse Understanding and Factual Consistency in Abstractive Summarization

Gabriel, Saadia and Bosselut, Antoine and Da, Jeff and Holtzman, Ari and Buys, Jan and Lo, Kyle and Celikyilmaz, Asli and Choi, Yejin (2021) Discourse Understanding and Factual Consistency in Abstractive Summarization, Proceedings of 16th Conference of the European Chapter of the Association for Computational Linguistics, April 19 - 23, 2021, Online.

[thumbnail of pdf] Other (pdf)
2021.eacl-main.34.pdf - Published Version

Download (495kB)

Abstract

We introduce a general framework for abstractive summarization with factual consistency and distinct modeling of the narrative flow in an output summary. Our work addresses current limitations of models for abstractive summarization that often hallucinate information or generate summaries with coherence issues. To generate abstractive summaries with fac- tual consistency and narrative flow, we propose Cooperative Generator – Discriminator Networks (Co-opNet), a novel transformer-based framework where a generator works with a discriminator architecture to compose coherent long-form summaries. We explore four different discriminator objectives which each capture a different aspect of coherence, including whether salient spans of generated abstracts are hallucinated or appear in the input context, and the likelihood of sentence adjacency in generated abstracts. We measure the ability of Co-opNet to learn these objectives with arXiv scientific papers, using the abstracts as a proxy for gold long-form scientific article summaries. Empirical results from automatic and human evaluations demonstrate that Co-opNet learns to summarize with considerably improved global coherence compared to competitive baselines.

Item Type: Conference paper
Subjects: Computing methodologies > Artificial intelligence > Natural language processing
Date Deposited: 03 Dec 2021 11:17
Last Modified: 03 Dec 2021 11:17
URI: https://pubs.cs.uct.ac.za/id/eprint/1489

Actions (login required)

View Item View Item