Controlling keywords and their positions in text generation
Yuichi Sasazawa, Terufumi Morishita, Hiroaki Ozaki, Osamu Imaichi, Yasuhiro Sogawa
Abstract
One of the challenges in text generation is to control text generation as intended by the user. Previous studies proposed specifying the keywords that should be included in the generated text. However, this approach is insufficient to generate text that reflect the user’s intent. For example, placing an important keyword at the beginning of the text would help attract the reader’s attention; however, existing methods do not enable such flexible control. In this paper, we tackle a novel task of controlling not only keywords but also the position of each keyword in the text generation. To this end, we propose a task-independent method that uses special tokens to control the relative position of keywords. Experimental results on summarization and story generation tasks show that the proposed method can control keywords and their positions. The experimental results also demonstrate that controlling the keyword positions can generate summary texts that are closer to the user’s intent than baseline.- Anthology ID:
- 2023.inlg-main.29
- Volume:
- Proceedings of the 16th International Natural Language Generation Conference
- Month:
- September
- Year:
- 2023
- Address:
- Prague, Czechia
- Editors:
- C. Maria Keet, Hung-Yi Lee, Sina Zarrieß
- Venues:
- INLG | SIGDIAL
- SIG:
- SIGGEN
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 407–413
- Language:
- URL:
- https://aclanthology.org/2023.inlg-main.29
- DOI:
- 10.18653/v1/2023.inlg-main.29
- Cite (ACL):
- Yuichi Sasazawa, Terufumi Morishita, Hiroaki Ozaki, Osamu Imaichi, and Yasuhiro Sogawa. 2023. Controlling keywords and their positions in text generation. In Proceedings of the 16th International Natural Language Generation Conference, pages 407–413, Prague, Czechia. Association for Computational Linguistics.
- Cite (Informal):
- Controlling keywords and their positions in text generation (Sasazawa et al., INLG-SIGDIAL 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2023.inlg-main.29.pdf