MProto: Multi-Prototype Network with Denoised Optimal Transport for Distantly Supervised Named Entity Recognition
This addresses the challenge of improving NER accuracy when only noisy, distantly supervised data is available, representing an incremental advance in prototype-based methods.
The paper tackles the problem of noisy distant supervision in named entity recognition by proposing MProto, a multi-prototype network with denoised optimal transport, which achieves state-of-the-art performance on several benchmarks.
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.