REVIEW 2 cited by
De-biasing Distantly Supervised Named Entity Recognition via Causal Intervention
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Distant supervision tackles the data bottleneck in NER by automatically generating training instances via dictionary matching. Unfortunately, the learning of DS-NER is severely dictionary-biased, which suffers from spurious correlations and therefore undermines the effectiveness and the robustness of the learned models. In this paper, we fundamentally explain the dictionary bias via a Structural Causal Model (SCM), categorize the bias into intra-dictionary and inter-dictionary biases, and identify their causes. Based on the SCM, we learn de-biased DS-NER via causal interventions. For intra-dictionary bias, we conduct backdoor adjustment to remove the spurious correlations introduced by the dictionary confounder. For inter-dictionary bias, we propose a causal invariance regularizer which will make DS-NER models more robust to the perturbation of dictionaries. Experiments on four datasets and three DS-NER models show that our method can significantly improve the performance of DS-NER.
Forward citations
Cited by 2 Pith papers
-
Towards DS-NER: Unveiling and Addressing Latent Noise in Distant Annotations
The paper introduces UES and NPE, a framework that treats unlabeled-entity and noisy-entity problems separately in distantly supervised NER, and reports average F1 gains over prior baselines.
-
Semi-Supervised Learning from Small Annotated Data and Large Unlabeled Data for Fine-grained PICO Entity Recognition
The paper shows that iterative pseudo-labeling with confidence, class-adaptive, or GPT-4o filtering can improve fine-grained PICO NER under 10% labeled data, though gains are modest and code is not released.
Discussion (0). Continue with ORCID to comment.