FPC: Fine-tuning with Prompt Curriculum for Relation Extraction

Sicheng Yang, Dandan Song


Abstract
The current classification methods for relation extraction (RE) generally utilize pre-trained language models (PLMs) and have achieved superior results. However, such methods directly treat relation labels as class numbers, therefore they ignore the semantics of relation labels. Recently, prompt-based fine-tuning has been proposed and attracted much attention. This kind of methods insert templates into the input and convert the classification task to a (masked) language modeling problem. With this inspiration, we propose a novel method Fine-tuning with Prompt Curriculum (FPC) for RE, with two distinctive characteristics: the relation prompt learning, introducing an auxiliary prompt-based fine-tuning task to make the model capture the semantics of relation labels; the prompt learning curriculum, a fine-tuning procedure including an increasingly difficult task to adapt the model to the difficult multi-task setting. We have conducted extensive experiments on four widely used RE benchmarks under fully supervised and low-resource settings. The experimental results show that FPC can significantly outperform the existing methods and obtain the new state-of-the-art results.
Anthology ID:
2022.aacl-main.78
Volume:
Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
November
Year:
2022
Address:
Online only
Venues:
AACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1065–1077
Language:
URL:
https://aclanthology.org/2022.aacl-main.78
DOI:
Bibkey:
Cite (ACL):
Sicheng Yang and Dandan Song. 2022. FPC: Fine-tuning with Prompt Curriculum for Relation Extraction. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 1065–1077, Online only. Association for Computational Linguistics.
Cite (Informal):
FPC: Fine-tuning with Prompt Curriculum for Relation Extraction (Yang & Song, AACL-IJCNLP 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2022.aacl-main.78.pdf