Discourse Understanding and Factual Consistency in Abstractive Summarization
Saadia Gabriel, Antoine Bosselut, Jeff Da, Ari Holtzman, Jan Buys, Kyle Lo, Asli Celikyilmaz, Yejin Choi
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 factual consistency and narrative flow, we propose Cooperative Generator-Discriminator Networks (Co-opNet), a novel transformer-based framework where the 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.- Anthology ID:
- 2021.eacl-main.34
- Volume:
- Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
- Month:
- April
- Year:
- 2021
- Address:
- Online
- Editors:
- Paola Merlo, Jorg Tiedemann, Reut Tsarfaty
- Venue:
- EACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 435–447
- Language:
- URL:
- https://aclanthology.org/2021.eacl-main.34
- DOI:
- 10.18653/v1/2021.eacl-main.34
- Cite (ACL):
- Saadia Gabriel, Antoine Bosselut, Jeff Da, Ari Holtzman, Jan Buys, Kyle Lo, Asli Celikyilmaz, and Yejin Choi. 2021. Discourse Understanding and Factual Consistency in Abstractive Summarization. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 435–447, Online. Association for Computational Linguistics.
- Cite (Informal):
- Discourse Understanding and Factual Consistency in Abstractive Summarization (Gabriel et al., EACL 2021)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/2021.eacl-main.34.pdf
- Data
- NEWSROOM