Comparing and combining some popular NER approaches on Biomedical tasks

Abstract

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 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 SEQ’s and SpanPred’s predictions, generating systems that 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.