BioBERT: a pre-trained biomedical language representation model for biomedical text mining

25 Jan 2019  ·  Jinhyuk Lee, Wonjin Yoon, Sungdong Kim, Donghyeon Kim, Sunkyu Kim, Chan Ho So, Jaewoo Kang ·

Biomedical text mining is becoming increasingly important as the number of biomedical documents rapidly grows. With the progress in natural language processing (NLP), extracting valuable information from biomedical literature has gained popularity among researchers, and deep learning has boosted the development of effective biomedical text mining models. However, directly applying the advancements in NLP to biomedical text mining often yields unsatisfactory results due to a word distribution shift from general domain corpora to biomedical corpora. In this article, we investigate how the recently introduced pre-trained language model BERT can be adapted for biomedical corpora. We introduce BioBERT (Bidirectional Encoder Representations from Transformers for Biomedical Text Mining), which is a domain-specific language representation model pre-trained on large-scale biomedical corpora. With almost the same architecture across tasks, BioBERT largely outperforms BERT and previous state-of-the-art models in a variety of biomedical text mining tasks when pre-trained on biomedical corpora. While BERT obtains performance comparable to that of previous state-of-the-art models, BioBERT significantly outperforms them on the following three representative biomedical text mining tasks: biomedical named entity recognition (0.62% F1 score improvement), biomedical relation extraction (2.80% F1 score improvement) and biomedical question answering (12.24% MRR improvement). Our analysis results show that pre-training BERT on biomedical corpora helps it to understand complex biomedical texts. We make the pre-trained weights of BioBERT freely available at https://github.com/naver/biobert-pretrained, and the source code for fine-tuning BioBERT available at https://github.com/dmis-lab/biobert.

PDF Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Benchmark
Relation Extraction ChemProt BioBERT F1 76.46 # 8
Drug–drug Interaction Extraction DDI extraction 2013 corpus BioBERT F1 0.8088 # 4
Micro F1 80.88 # 4
Named Entity Recognition (NER) JNLPBA BioBERT F1 77.59 # 13
Zero-Shot Learning MedConceptsQA dmis-lab/biobert-v1.1 Accuracy 26.151 # 3
Few-Shot Learning MedConceptsQA dmis-lab/biobert-v1.1 Accuracy 25.458 # 6
Question Answering MedQA BioBERT (large) Accuracy 36.7 # 22
Question Answering MedQA BioBERT (base) Accuracy 34.1 # 23
Named Entity Recognition (NER) NCBI-disease BioBERT F1 89.71 # 5
Representation Learning SciDocs BioBERT Avg. 58.8 # 6

Methods