Distilling Causal Effect from Miscellaneous Other-Class for Continual Named Entity Recognition
Continual Learning for Named Entity Recognition (CL-NER) aims to learn a growing number of entity types over time from a stream of data. However, simply learning Other-Class in the same way as new entity types amplifies the catastrophic forgetting and leads to a substantial performance drop. The main cause behind this is that Other-Class samples usually contain old entity types, and the old knowledge in these Other-Class samples is not preserved properly. Thanks to the causal inference, we identify that the forgetting is caused by the missing causal effect from the old data. To this end, we propose a unified causal framework to retrieve the causality from both new entity types and Other-Class. Furthermore, we apply curriculum learning to mitigate the impact of label noise and introduce a self-adaptive weight for balancing the causal effects between new entity types and Other-Class. Experimental results on three benchmark datasets show that our method outperforms the state-of-the-art method by a large margin. Moreover, our method can be combined with the existing state-of-the-art methods to improve the performance in CL-NER
Code (1)
Tasks
Causal InferenceContinual LearningContinual Named Entity RecognitionFG-1-PG-1Miscellaneousnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)NERSimilar Papers 제목 키워드 기반
Distilling interpretable causal trees from causal forests
Machine learning methods for estimating treatment effect heterogeneity promise greater flexibility than existing methods that test a few pre-specified hypotheses. However, one problem these methods can have is that it ca…
Evaluating Large Language Models for Causal Modeling
In this paper, we consider the process of transforming causal domain knowledge into a representation that aligns more closely with guidelines from causal data science. To this end, we introduce two novel tasks related to…
Distilling Causal Effect of Data in Class-Incremental Learning
We propose a causal framework to explain the catastrophic forgetting in Class-Incremental Learning (CIL) and then derive a novel distillation method that is orthogonal to the existing anti-forgetting techniques, such as …
class-incremental learningClass Incremental LearningIncremental LearningJoint Statistical and Causal Feature Modulated Face Anti-Spoofing
In this paper, we propose a hierarchical feature modulation (HFM) approach for stable face anti-spoofing in unseen domains and unseen attacks. The conventional multi-domain based generalizable approaches likely lead to l…
Face Anti-SpoofingMiscellaneousTargeted VAE: Variational and Targeted Learning for Causal Inference
Undertaking causal inference with observational data is incredibly useful across a wide range of tasks including the development of medical treatments, advertisements and marketing, and policy making. There are two signi…
Causal InferencecounterfactualMarketingMiscellaneous