Improving Abstraction in Text Summarization

Wojciech Kryściński, Romain Paulus, Caiming Xiong, Richard Socher


Abstract
Abstractive text summarization aims to shorten long text documents into a human readable form that contains the most important facts from the original document. However, the level of actual abstraction as measured by novel phrases that do not appear in the source document remains low in existing approaches. We propose two techniques to improve the level of abstraction of generated summaries. First, we decompose the decoder into a contextual network that retrieves relevant parts of the source document, and a pretrained language model that incorporates prior knowledge about language generation. Second, we propose a novelty metric that is optimized directly through policy learning to encourage the generation of novel phrases. Our model achieves results comparable to state-of-the-art models, as determined by ROUGE scores and human evaluations, while achieving a significantly higher level of abstraction as measured by n-gram overlap with the source document.
Anthology ID:
D18-1207
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Editors:
Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1808–1817
Language:
URL:
https://aclanthology.org/D18-1207
DOI:
10.18653/v1/D18-1207
Bibkey:
Cite (ACL):
Wojciech Kryściński, Romain Paulus, Caiming Xiong, and Richard Socher. 2018. Improving Abstraction in Text Summarization. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 1808–1817, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Improving Abstraction in Text Summarization (Kryściński et al., EMNLP 2018)
Copy Citation:
PDF:
https://aclanthology.org/D18-1207.pdf
Video:
 https://aclanthology.org/D18-1207.mp4
Data
CNN/Daily Mail