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

研究成果: Conference contribution

抜粋

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, since it differs from users to users what they are interested in, it is necessary to develop a method to generate various summaries according to users’ requests. 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., Nikkei 225), 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. Experiments show both models using additional information of target document achieved higher performance in terms of BLEU and human evaluation. We found that human-designed topic labels are superior to extracted keywords in terms of controllability.

元の言語English
ホスト出版物のタイトルINLG 2019 - 12th International Conference on Natural Language Generation, Proceedings of the Conference
出版者Association for Computational Linguistics (ACL)
ページ323-332
ページ数10
ISBN(電子版)9781950737949
出版物ステータスPublished - 2019
イベント12th International Conference on Natural Language Generation, INLG 2019 - Tokyo, Japan
継続期間: 2019 10 292019 11 1

出版物シリーズ

名前INLG 2019 - 12th International Conference on Natural Language Generation, Proceedings of the Conference

Conference

Conference12th International Conference on Natural Language Generation, INLG 2019
Japan
Tokyo
期間19/10/2919/11/1

ASJC Scopus subject areas

  • Software

フィンガープリント Controlling contents in data-to-document generation with human-designed topic labels' の研究トピックを掘り下げます。これらはともに一意のフィンガープリントを構成します。

  • これを引用

    Aoki, K., Miyazawa, A., Ishigaki, T., Aoki, T., Noji, H., Goshima, K., Kobayashi, I., Takamura, H., & Miyao, Y. (2019). Controlling contents in data-to-document generation with human-designed topic labels. : INLG 2019 - 12th International Conference on Natural Language Generation, Proceedings of the Conference (pp. 323-332). (INLG 2019 - 12th International Conference on Natural Language Generation, Proceedings of the Conference). Association for Computational Linguistics (ACL).