Keeping Consistency of Sentence Generation and Document Classification with Multi-Task Learning

Toru Nishino, Shotaro Misawa, Ryuji Kano, Tomoki Taniguchi, Yasuhide Miura, Tomoko Ohkuma


Abstract
The automated generation of information indicating the characteristics of articles such as headlines, key phrases, summaries and categories helps writers to alleviate their workload. Previous research has tackled these tasks using neural abstractive summarization and classification methods. However, the outputs may be inconsistent if they are generated individually. The purpose of our study is to generate multiple outputs consistently. We introduce a multi-task learning model with a shared encoder and multiple decoders for each task. We propose a novel loss function called hierarchical consistency loss to maintain consistency among the attention weights of the decoders. To evaluate the consistency, we employ a human evaluation. The results show that our model generates more consistent headlines, key phrases and categories. In addition, our model outperforms the baseline model on the ROUGE scores, and generates more adequate and fluent headlines.
Anthology ID:
D19-1315
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:
3195–3205
Language:
URL:
https://aclanthology.org/D19-1315
DOI:
10.18653/v1/D19-1315
Bibkey:
Cite (ACL):
Toru Nishino, Shotaro Misawa, Ryuji Kano, Tomoki Taniguchi, Yasuhide Miura, and Tomoko Ohkuma. 2019. Keeping Consistency of Sentence Generation and Document Classification with Multi-Task Learning. 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 3195–3205, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Keeping Consistency of Sentence Generation and Document Classification with Multi-Task Learning (Nishino et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/D19-1315.pdf
Attachment:
 D19-1315.Attachment.pdf