Comparing and combining some popular NER approaches on Biomedical tasks
This work provides an incremental comparison and combination of existing NER methods for biomedical text processing, particularly benefiting researchers in that domain.
The paper compared three named entity recognition (NER) approaches on biomedical tasks, finding that SpanPred and SeqCRF achieved state-of-the-art performance on Spanish datasets with F1 improvements of up to 1.3, and a learned combiner system boosted F1 by 1.2 on the GENIA dataset.
We compare three simple and popular approaches for NER: 1) SEQ (sequence-labeling with a linear token classifier) 2) SeqCRF (sequence-labeling with Conditional Random Fields), and 3) SpanPred (span-prediction with boundary token embeddings). We compare the approaches on 4 biomedical NER tasks: GENIA, NCBI-Disease, LivingNER (Spanish), and SocialDisNER (Spanish). The SpanPred model demonstrates state-of-the-art performance on LivingNER and SocialDisNER, improving F1 by 1.3 and 0.6 F1 respectively. The SeqCRF model also demonstrates state-of-the-art performance on LivingNER and SocialDisNER, improving F1 by 0.2 F1 and 0.7 respectively. The SEQ model is competitive with the state-of-the-art on the LivingNER dataset. We explore some simple ways of combining the three approaches. We find that majority voting consistently gives high precision and high F1 across all 4 datasets. Lastly, we implement a system that learns to combine the predictions of SEQ and SpanPred, generating systems that consistently give high recall and high F1 across all 4 datasets. On the GENIA dataset, we find that our learned combiner system significantly boosts F1(+1.2) and recall(+2.1) over the systems being combined. We release all the well-documented code necessary to reproduce all systems at https://github.com/flyingmothman/bionlp.