Neural Extractive Text Summarization with Syntactic Compression

Jiacheng Xu, Greg Durrett


Abstract
Recent neural network approaches to summarization are largely either selection-based extraction or generation-based abstraction. In this work, we present a neural model for single-document summarization based on joint extraction and syntactic compression. Our model chooses sentences from the document, identifies possible compressions based on constituency parses, and scores those compressions with a neural model to produce the final summary. For learning, we construct oracle extractive-compressive summaries, then learn both of our components jointly with this supervision. Experimental results on the CNN/Daily Mail and New York Times datasets show that our model achieves strong performance (comparable to state-of-the-art systems) as evaluated by ROUGE. Moreover, our approach outperforms an off-the-shelf compression module, and human and manual evaluation shows that our model’s output generally remains grammatical.
Anthology ID:
D19-1324
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
3292–3303
Language:
URL:
https://aclanthology.org/D19-1324
DOI:
10.18653/v1/D19-1324
Bibkey:
Cite (ACL):
Jiacheng Xu and Greg Durrett. 2019. Neural Extractive Text Summarization with Syntactic Compression. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 3292–3303, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Neural Extractive Text Summarization with Syntactic Compression (Xu & Durrett, EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1324.pdf
Attachment:
 D19-1324.Attachment.pdf
Code
 jiacheng-xu/neu-compression-sum
Data
New York Times Annotated Corpus