ACL 2023short10 citations

Focused Prefix Tuning for Controllable Text Generation

Congda Ma, Tianyu Zhao, Makoto Shing, Kei Sawada, Manabu Okumura

Abstract

In a controllable text generation dataset, there exist unannotated attributes that could provide irrelevant learning signals to models that use it for training and thus degrade their performance. We propose focused prefix tuning (FPT) to mitigate the problem and to enable the control to focus on the desired attribute. Experimental results show that FPT can achieve better control accuracy and text fluency than baseline models in single-attribute control tasks. In multi-attribute control tasks, FPT achieves comparable control accuracy with the state-of-the-art approach while keeping the flexibility to control new attributes without retraining existing models.

BibTeX
@inproceedings{ma-etal-2023-focused,
    title = "Focused Prefix Tuning for Controllable Text Generation",
    author = "Ma, Congda  and
      Zhao, Tianyu  and
      Shing, Makoto  and
      Sawada, Kei  and
      Okumura, Manabu",
    editor = "Rogers, Anna  and
      Boyd-Graber, Jordan  and
      Okazaki, Naoaki",
    booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.acl-short.96/",
    doi = "10.18653/v1/2023.acl-short.96",
    pages = "1116--1127"
}
Focused Prefix Tuning for Controllable Text Generation · ACL 2023