Learning from Miscellaneous Other-Class Words for Few-shot Named Entity Recognition
This work improves few-shot NER, a key task in natural language processing for extracting entities with limited annotations, by enhancing discriminative ability and reducing overfitting, though it is incremental as it builds on prototypical networks.
The paper tackles the problem of few-shot named entity recognition (NER) by addressing the failure of existing prototypical methods to differentiate semantics in other-class words, which causes overfitting. The proposed MUCO model automatically induces undefined classes from the other class, outperforming five state-of-the-art models in 1-shot and 5-shot settings on four benchmarks.
Few-shot Named Entity Recognition (NER) exploits only a handful of annotations to identify and classify named entity mentions. Prototypical network shows superior performance on few-shot NER. However, existing prototypical methods fail to differentiate rich semantics in other-class words, which will aggravate overfitting under few shot scenario. To address the issue, we propose a novel model, Mining Undefined Classes from Other-class (MUCO), that can automatically induce different undefined classes from the other class to improve few-shot NER. With these extra-labeled undefined classes, our method will improve the discriminative ability of NER classifier and enhance the understanding of predefined classes with stand-by semantic knowledge. Experimental results demonstrate that our model outperforms five state-of-the-art models in both 1-shot and 5-shots settings on four NER benchmarks. We will release the code upon acceptance. The source code is released on https: //github.com/shuaiwa16/OtherClassNER.git.