Controlling Contents in Data-to-Document Generation with Human-Designed Topic Labels

Kasumi Aoki, Akira Miyazawa, Tatsuya Ishigaki, Tatsuya Aoki, Hiroshi Noji, Keiichi Goshima, Ichiro Kobayashi, Hiroya Takamura, Yusuke Miyao


Abstract
We propose a data-to-document generator that can easily control the contents of output texts based on a neural language model. Conventional data-to-text model is useful when a reader seeks a global summary of data because it has only to describe an important part that has been extracted beforehand. However, because depending on users, it differs what they are interested in, so it is necessary to develop a method to generate various summaries according to users’ interests. We develop a model to generate various summaries and to control their contents by providing the explicit targets for a reference to the model as controllable factors. In the experiments, we used five-minute or one-hour charts of 9 indicators (e.g., Nikkei225), as time-series data, and daily summaries of Nikkei Quick News as textual data. We conducted comparative experiments using two pieces of information: human-designed topic labels indicating the contents of a sentence and automatically extracted keywords as the referential information for generation.
Anthology ID:
W19-8640
Volume:
Proceedings of the 12th International Conference on Natural Language Generation
Month:
October–November
Year:
2019
Address:
Tokyo, Japan
Editors:
Kees van Deemter, Chenghua Lin, Hiroya Takamura
Venue:
INLG
SIG:
SIGGEN
Publisher:
Association for Computational Linguistics
Note:
Pages:
323–332
Language:
URL:
https://aclanthology.org/W19-8640
DOI:
10.18653/v1/W19-8640
Bibkey:
Cite (ACL):
Kasumi Aoki, Akira Miyazawa, Tatsuya Ishigaki, Tatsuya Aoki, Hiroshi Noji, Keiichi Goshima, Ichiro Kobayashi, Hiroya Takamura, and Yusuke Miyao. 2019. Controlling Contents in Data-to-Document Generation with Human-Designed Topic Labels. In Proceedings of the 12th International Conference on Natural Language Generation, pages 323–332, Tokyo, Japan. Association for Computational Linguistics.
Cite (Informal):
Controlling Contents in Data-to-Document Generation with Human-Designed Topic Labels (Aoki et al., INLG 2019)
Copy Citation:
PDF:
https://aclanthology.org/W19-8640.pdf