Improving Distantly-Supervised Named Entity Recognition with Self-Collaborative Denoising Learning
This work addresses label noise in DS-NER, a domain-specific issue for natural language processing, with incremental improvements over prior methods.
The paper tackles the problem of label noise in distantly supervised named entity recognition, which arises from incomplete and inaccurate annotations, by proposing a Self-Collaborative Denoising Learning method that outperforms state-of-the-art denoising approaches on five real-world datasets.
Distantly supervised named entity recognition (DS-NER) efficiently reduces labor costs but meanwhile intrinsically suffers from the label noise due to the strong assumption of distant supervision. Typically, the wrongly labeled instances comprise numbers of incomplete and inaccurate annotation noise, while most prior denoising works are only concerned with one kind of noise and fail to fully explore useful information in the whole training set. To address this issue, we propose a robust learning paradigm named Self-Collaborative Denoising Learning (SCDL), which jointly trains two teacher-student networks in a mutually-beneficial manner to iteratively perform noisy label refinery. Each network is designed to exploit reliable labels via self denoising, and two networks communicate with each other to explore unreliable annotations by collaborative denoising. Extensive experimental results on five real-world datasets demonstrate that SCDL is superior to state-of-the-art DS-NER denoising methods.