Automatic Label Sequence Generation for Prompting Sequence-to-sequence Models

Zichun Yu, Tianyu Gao, Zhengyan Zhang, Yankai Lin, Zhiyuan Liu, Maosong Sun, Jie Zhou


Abstract
Prompting, which casts downstream applications as language modeling tasks, has shown to be sample efficient compared to standard fine-tuning with pre-trained models. However, one pitfall of prompting is the need of manually-designed patterns, whose outcome can be unintuitive and requires large validation sets to tune. To tackle the challenge, we propose AutoSeq, a fully automatic prompting method: (1) We adopt natural language prompts on sequence-to-sequence models, enabling free-form generation and larger label search space; (2) We propose label sequences – phrases with indefinite lengths to verbalize the labels – which eliminate the need of manual templates and are more expressive than single label words; (3) We use beam search to automatically generate a large amount of label sequence candidates and propose contrastive re-ranking to get the best combinations. AutoSeq significantly outperforms other no-manual-design methods, such as soft prompt tuning, adapter tuning, and automatic search on single label words; the generated label sequences are even better than curated manual ones on a variety of tasks. Our method reveals the potential of sequence-to-sequence models in few-shot learning and sheds light on a path to generic and automatic prompting. The source code of this paper can be obtained from https://github.com/thunlp/Seq2Seq-Prompt.
Anthology ID:
2022.coling-1.440
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
4965–4975
Language:
URL:
https://aclanthology.org/2022.coling-1.440
DOI:
Bibkey:
Cite (ACL):
Zichun Yu, Tianyu Gao, Zhengyan Zhang, Yankai Lin, Zhiyuan Liu, Maosong Sun, and Jie Zhou. 2022. Automatic Label Sequence Generation for Prompting Sequence-to-sequence Models. In Proceedings of the 29th International Conference on Computational Linguistics, pages 4965–4975, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Automatic Label Sequence Generation for Prompting Sequence-to-sequence Models (Yu et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.440.pdf
Code
 thunlp/seq2seq-prompt
Data
GLUEMultiRCReCoRDSNLISSTSuperGLUEWSC