Extractive Summarization with SWAP-NET: Sentences and Words from Alternating Pointer Networks

Aishwarya Jadhav, Vaibhav Rajan


Abstract
We present a new neural sequence-to-sequence model for extractive summarization called SWAP-NET (Sentences and Words from Alternating Pointer Networks). Extractive summaries comprising a salient subset of input sentences, often also contain important key words. Guided by this principle, we design SWAP-NET that models the interaction of key words and salient sentences using a new two-level pointer network based architecture. SWAP-NET identifies both salient sentences and key words in an input document, and then combines them to form the extractive summary. Experiments on large scale benchmark corpora demonstrate the efficacy of SWAP-NET that outperforms state-of-the-art extractive summarizers.
Anthology ID:
P18-1014
Volume:
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2018
Address:
Melbourne, Australia
Editors:
Iryna Gurevych, Yusuke Miyao
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
142–151
Language:
URL:
https://aclanthology.org/P18-1014
DOI:
10.18653/v1/P18-1014
Bibkey:
Cite (ACL):
Aishwarya Jadhav and Vaibhav Rajan. 2018. Extractive Summarization with SWAP-NET: Sentences and Words from Alternating Pointer Networks. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 142–151, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):
Extractive Summarization with SWAP-NET: Sentences and Words from Alternating Pointer Networks (Jadhav & Rajan, ACL 2018)
Copy Citation:
PDF:
https://aclanthology.org/P18-1014.pdf
Video:
 https://aclanthology.org/P18-1014.mp4
Data
CNN/Daily Mail