Extractive Summarization Using Multi-Task Learning with Document Classification

Masaru Isonuma, Toru Fujino, Junichiro Mori, Yutaka Matsuo, Ichiro Sakata


Abstract
The need for automatic document summarization that can be used for practical applications is increasing rapidly. In this paper, we propose a general framework for summarization that extracts sentences from a document using externally related information. Our work is aimed at single document summarization using small amounts of reference summaries. In particular, we address document summarization in the framework of multi-task learning using curriculum learning for sentence extraction and document classification. The proposed framework enables us to obtain better feature representations to extract sentences from documents. We evaluate our proposed summarization method on two datasets: financial report and news corpus. Experimental results demonstrate that our summarizers achieve performance that is comparable to state-of-the-art systems.
Anthology ID:
D17-1223
Volume:
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
2101–2110
Language:
URL:
https://aclanthology.org/D17-1223
DOI:
10.18653/v1/D17-1223
Bibkey:
Cite (ACL):
Masaru Isonuma, Toru Fujino, Junichiro Mori, Yutaka Matsuo, and Ichiro Sakata. 2017. Extractive Summarization Using Multi-Task Learning with Document Classification. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2101–2110, Copenhagen, Denmark. Association for Computational Linguistics.
Cite (Informal):
Extractive Summarization Using Multi-Task Learning with Document Classification (Isonuma et al., EMNLP 2017)
Copy Citation:
PDF:
https://aclanthology.org/D17-1223.pdf