MProto: Multi-Prototype Network with Denoised Optimal Transport for Distantly Supervised Named Entity Recognition

Shuhui Wu, Yongliang Shen, Zeqi Tan, Wenqi Ren, Jietian Guo, Shiliang Pu, Weiming Lu


Abstract
Distantly supervised named entity recognition (DS-NER) aims to locate entity mentions and classify their types with only knowledge bases or gazetteers and unlabeled corpus. However, distant annotations are noisy and degrade the performance of NER models. In this paper, we propose a noise-robust prototype network named MProto for the DS-NER task. Different from previous prototype-based NER methods, MProto represents each entity type with multiple prototypes to characterize the intra-class variance among entity representations. To optimize the classifier, each token should be assigned an appropriate ground-truth prototype and we consider such token-prototype assignment as an optimal transport (OT) problem. Furthermore, to mitigate the noise from incomplete labeling, we propose a novel denoised optimal transport (DOT) algorithm. Specifically, we utilize the assignment result between *Other* class tokens and all prototypes to distinguish unlabeled entity tokens from true negatives. Experiments on several DS-NER benchmarks demonstrate that our MProto achieves state-of-the-art performance. The source code is now available on Github.
Anthology ID:
2023.emnlp-main.145
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2361–2374
Language:
URL:
https://aclanthology.org/2023.emnlp-main.145
DOI:
10.18653/v1/2023.emnlp-main.145
Bibkey:
Cite (ACL):
Shuhui Wu, Yongliang Shen, Zeqi Tan, Wenqi Ren, Jietian Guo, Shiliang Pu, and Weiming Lu. 2023. MProto: Multi-Prototype Network with Denoised Optimal Transport for Distantly Supervised Named Entity Recognition. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 2361–2374, Singapore. Association for Computational Linguistics.
Cite (Informal):
MProto: Multi-Prototype Network with Denoised Optimal Transport for Distantly Supervised Named Entity Recognition (Wu et al., EMNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.emnlp-main.145.pdf
Video:
 https://aclanthology.org/2023.emnlp-main.145.mp4