Order-Agnostic Data Augmentation for Few-Shot Named Entity Recognition

Huiming Wang, Liying Cheng, Wenxuan Zhang, De Wen Soh, Lidong Bing


Abstract
Data augmentation (DA) methods have been proven to be effective for pre-trained language models (PLMs) in low-resource settings, including few-shot named entity recognition (NER). However, existing NER DA techniques either perform rule-based manipulations on words that break the semantic coherence of the sentence, or exploit generative models for entity or context substitution, which requires a substantial amount of labeled data and contradicts the objective of operating in low-resource settings. In this work, we propose order-agnostic data augmentation (OaDA), an alternative solution that exploits the often overlooked order-agnostic property in the training data construction phase of sequence-to-sequence NER methods for data augmentation. To effectively utilize the augmented data without suffering from the one-to-many issue, where multiple augmented target sequences exist for one single sentence, we further propose the use of ordering instructions and an innovative OaDA-XE loss. Specifically, by treating each permutation of entity types as an ordering instruction, we rearrange the entity set accordingly, ensuring a distinct input-output pair, while OaDA-XE assigns loss based on the best match between the target sequence and model predictions. We conduct comprehensive experiments and analyses across three major NER benchmarks and significantly enhance the few-shot capabilities of PLMs with OaDA.
Anthology ID:
2024.acl-long.421
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7792–7807
Language:
URL:
https://preview.aclanthology.org/build-pipeline-with-new-library/2024.acl-long.421/
DOI:
10.18653/v1/2024.acl-long.421
Bibkey:
Cite (ACL):
Huiming Wang, Liying Cheng, Wenxuan Zhang, De Wen Soh, and Lidong Bing. 2024. Order-Agnostic Data Augmentation for Few-Shot Named Entity Recognition. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 7792–7807, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Order-Agnostic Data Augmentation for Few-Shot Named Entity Recognition (Wang et al., ACL 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/build-pipeline-with-new-library/2024.acl-long.421.pdf