Adversarial Demonstration Learning for Low-resource NER Using Dual Similarity
This work improves NER performance in low-resource scenarios, which is important for applications with limited labeled data, though it appears incremental as it builds on existing demonstration learning methods.
The paper tackles low-resource named entity recognition (NER) by addressing issues in demonstration construction and model training, proposing a dual similarity selection and adversarial training approach that outperforms existing methods.
We study the problem of named entity recognition (NER) based on demonstration learning in low-resource scenarios. We identify two issues in demonstration construction and model training. Firstly, existing methods for selecting demonstration examples primarily rely on semantic similarity; We show that feature similarity can provide significant performance improvement. Secondly, we show that the NER tagger's ability to reference demonstration examples is generally inadequate. We propose a demonstration and training approach that effectively addresses these issues. For the first issue, we propose to select examples by dual similarity, which comprises both semantic similarity and feature similarity. For the second issue, we propose to train an NER model with adversarial demonstration such that the model is forced to refer to the demonstrations when performing the tagging task. We conduct comprehensive experiments in low-resource NER tasks, and the results demonstrate that our method outperforms a range of methods.