Global Optimization under Length Constraint for Neural Text Summarization

Takuya Makino, Tomoya Iwakura, Hiroya Takamura, Manabu Okumura


Abstract
We propose a global optimization method under length constraint (GOLC) for neural text summarization models. GOLC increases the probabilities of generating summaries that have high evaluation scores, ROUGE in this paper, within a desired length. We compared GOLC with two optimization methods, a maximum log-likelihood and a minimum risk training, on CNN/Daily Mail and a Japanese single document summarization data set of The Mainichi Shimbun Newspapers. The experimental results show that a state-of-the-art neural summarization model optimized with GOLC generates fewer overlength summaries while maintaining the fastest processing speed; only 6.70% overlength summaries on CNN/Daily and 7.8% on long summary of Mainichi, compared to the approximately 20% to 50% on CNN/Daily Mail and 10% to 30% on Mainichi with the other optimization methods. We also demonstrate the importance of the generation of in-length summaries for post-editing with the dataset Mainich that is created with strict length constraints. The ex- perimental results show approximately 30% to 40% improved post-editing time by use of in-length summaries.
Anthology ID:
P19-1099
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1039–1048
Language:
URL:
https://aclanthology.org/P19-1099
DOI:
10.18653/v1/P19-1099
Bibkey:
Cite (ACL):
Takuya Makino, Tomoya Iwakura, Hiroya Takamura, and Manabu Okumura. 2019. Global Optimization under Length Constraint for Neural Text Summarization. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 1039–1048, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Global Optimization under Length Constraint for Neural Text Summarization (Makino et al., ACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/P19-1099.pdf
Video:
 https://vimeo.com/384475549