| title | booktitle | year | volume | series | month | publisher | url | software | openreview | abstract | layout | issn | id | tex_title | firstpage | lastpage | page | order | cycles | bibtex_editor | editor | bibtex_author | author | date | address | container-title | genre | issued | extras | ||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
LabelPrompt: Effective prompt-based learning for relation classification |
Proceedings of the 16th Asian Conference on Machine Learning |
2025 |
260 |
Proceedings of Machine Learning Research |
0 |
PMLR |
XOAuohgWlR |
Recently, prompt-based learning has become popular in many Natural Language Processing (NLP) tasks by converting the task into a cloze-style one to smooth out the differences between Pre-trained Language Models (PLMs) and the current task. However, as for relation classification, it is challenging to associate the natural language word that fills in the mask token with relation labels due to the rich semantic information in textual label, e.g. ”org:founded_by”. To address this challenge, this paper presents a novel prompt-based learning method, namely LabelPrompt, for the relation classification task. It is an extraordinary intuitive approach motivated by “GIVE MODEL CHOICES!”. Specifically, we first define additional tokens to represent the relation labels, which regard these tokens as the verbalizer with semantic initialisation and explicitly construct them with a prompt template method. Then, we address the inconsistency between predicted relations and given entities by implementing an entity-aware module that employs contrastive learning. Last, we conduct an attention query strategy to differentiate prompt tokens and sequence tokens. These strategies effectively improve the adaptation capability of prompt-based learning, especially when only a small labelled dataset is available. Extensive experimental results obtained on several bench-marking datasets demonstrate the superiority of our method, particularly in the few-shot scenario. Our code can be found at \url{https://github.com/xerrors/Labelprompt}. |
inproceedings |
2640-3498 |
zhang25c |
{LabelPrompt}: {E}ffective prompt-based learning for relation classification |
1304 |
1319 |
1304-1319 |
1304 |
false |
Nguyen, Vu and Lin, Hsuan-Tien |
|
Zhang, Wenjie and Song, Xiaoning and Feng, Zhenhua and Xu, Tianyang and Wu, Xiaojun |
|
2025-01-14 |
Proceedings of the 16th Asian Conference on Machine Learning |
inproceedings |
|
|