A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents

Arman Cohan, Franck Dernoncourt, Doo Soon Kim, Trung Bui, Seokhwan Kim, Walter Chang, Nazli Goharian

[How to correct problems with metadata yourself]


Abstract
Neural abstractive summarization models have led to promising results in summarizing relatively short documents. We propose the first model for abstractive summarization of single, longer-form documents (e.g., research papers). Our approach consists of a new hierarchical encoder that models the discourse structure of a document, and an attentive discourse-aware decoder to generate the summary. Empirical results on two large-scale datasets of scientific papers show that our model significantly outperforms state-of-the-art models.
Anthology ID:
N18-2097
Volume:
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)
Month:
June
Year:
2018
Address:
New Orleans, Louisiana
Editors:
Marilyn Walker, Heng Ji, Amanda Stent
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
615–621
Language:
URL:
https://aclanthology.org/N18-2097
DOI:
10.18653/v1/N18-2097
Bibkey:
Cite (ACL):
Arman Cohan, Franck Dernoncourt, Doo Soon Kim, Trung Bui, Seokhwan Kim, Walter Chang, and Nazli Goharian. 2018. A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 615–621, New Orleans, Louisiana. Association for Computational Linguistics.
Cite (Informal):
A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents (Cohan et al., NAACL 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/teach-a-man-to-fish/N18-2097.pdf
Code
 acohan/long-summarization +  additional community code
Data
arXiv Summarization DatasetArxiv HEP-TH citation graphCNN/Daily MailPubmed