Named Entity Recognition in the Style of Object Detection
This addresses nested NER, a challenging problem in NLP, by borrowing from computer vision, though it is an incremental adaptation.
The authors tackled nested named entity recognition by adapting a two-stage object detection approach, achieving F1 scores of 85.6% on ACE2005 and 76.8% on Genia.
In this work, we propose a two-stage method for named entity recognition (NER), especially for nested NER. We borrowed the idea from the two-stage Object Detection in computer vision and the way how they construct the loss function. First, a region proposal network generates region candidates and then a second-stage model discriminates and classifies the entity and makes the final prediction. We also designed a special loss function for the second-stage training that predicts the entityness and entity type at the same time. The model is built on top of pretrained BERT encoders, and we tried both BERT base and BERT large models. For experiments, we first applied it to flat NER tasks such as CoNLL2003 and OntoNotes 5.0 and got comparable results with traditional NER models using sequence labeling methodology. We then tested the model on the nested named entity recognition task ACE2005 and Genia, and got F1 score of 85.6$\%$ and 76.8$\%$ respectively. In terms of the second-stage training, we found that adding extra randomly selected regions plays an important role in improving the precision. We also did error profiling to better evaluate the performance of the model in different circumstances for potential improvements in the future.