AutoTriggER: Label-Efficient and Robust Named Entity Recognition with Auxiliary Trigger Extraction
This work addresses label efficiency and robustness for NER practitioners, offering an incremental improvement over existing methods.
The paper tackled the problem of label scarcity and generalization in named entity recognition by automatically generating entity triggers to guide models, resulting in an average improvement of nearly 0.5 F1 points over a baseline on three datasets.
Deep neural models for named entity recognition (NER) have shown impressive results in overcoming label scarcity and generalizing to unseen entities by leveraging distant supervision and auxiliary information such as explanations. However, the costs of acquiring such additional information are generally prohibitive. In this paper, we present a novel two-stage framework (AutoTriggER) to improve NER performance by automatically generating and leveraging ``entity triggers'' which are human-readable cues in the text that help guide the model to make better decisions. Our framework leverages post-hoc explanation to generate rationales and strengthens a model's prior knowledge using an embedding interpolation technique. This approach allows models to exploit triggers to infer entity boundaries and types instead of solely memorizing the entity words themselves. Through experiments on three well-studied NER datasets, AutoTriggER shows strong label-efficiency, is capable of generalizing to unseen entities, and outperforms the RoBERTa-CRF baseline by nearly 0.5 F1 points on average.