paper-with-me

Papers

De-biasing Distantly Supervised Named Entity Recognition via Causal Intervention

2021-06-17 · ACL 2021 5 · Wenkai Zhang, Hongyu Lin, Xianpei Han, Le Sun

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.

📄 PDF Abstract BibTeX arXiv:2106.09233

Code (1)

zwkatgithub/DSCAU 공식 구현 pytorch

Tasks

named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)NER

Similar Papers 제목 키워드 기반

Distantly-Supervised Named Entity Recognition with Noise-Robust Learning and Language Model Augmented Self-Training

2021-09-10 · EMNLP 2021 11 · Yu Meng, Yunyi Zhang, Jiaxin Huang, Xuan Wang 외

We study the problem of training named entity recognition (NER) models using only distantly-labeled data, which can be automatically obtained by matching entity mentions in the raw text with entity types in a knowledge b…

Language ModelingLanguage Modellingnamed-entity-recognitionNamed Entity Recognition+2

Better Sampling of Negatives for Distantly Supervised Named Entity Recognition

2023-05-22 · Lu Xu, Lidong Bing, Wei Lu

Distantly supervised named entity recognition (DS-NER) has been proposed to exploit the automatically labeled training data instead of human annotations. The distantly annotated datasets are often noisy and contain a con…

named-entity-recognitionNamed Entity RecognitionNER

HAMNER: Headword Amplified Multi-span Distantly Supervised Method for Domain Specific Named Entity Recognition

2019-12-03 · Shifeng Liu, Yifang Sun, Bing Li, Wei Wang 외

To tackle Named Entity Recognition (NER) tasks, supervised methods need to obtain sufficient cleanly annotated data, which is labor and time consuming. On the contrary, distantly supervised methods acquire automatically …

Boundary Detectionnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)+1

TEBNER: Domain Specific Named Entity Recognition with Type Expanded Boundary-aware Network

2021-11-01 · EMNLP 2021 11 · Zheng Fang, Yanan Cao, Tai Li, Ruipeng Jia 외

To alleviate label scarcity in Named Entity Recognition (NER) task, distantly supervised NER methods are widely applied to automatically label data and identify entities. Although the human effort is reduced, the generat…

named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)NER

Distantly Supervised Named Entity Recognition via Confidence-Based Multi-Class Positive and Unlabeled Learning

2021-11-16 · ACL ARR November 2021 11 · Anonymous

In this paper, we study the named entity recognition (NER) problem under distant supervision. Due to the incompleteness of the external dictionaries and/or knowledge bases, such distantly annotated training data usually …

named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)NER