Papers › Improving Biomedical Pretrained Language Models with Knowledge

Improving Biomedical Pretrained Language Models with Knowledge

21 Apr 2021NAACL (BioNLP) 2021 6arXiv:2104.10344archive 2025-07-28

Zheng Yuan, Yijia Liu, Chuanqi Tan, Songfang Huang, Fei Huang

Pretrained language models have shown success in many natural language processing tasks. Many works explore incorporating knowledge into language models. In the biomedical domain, experts have taken decades of effort on building large-scale knowledge bases. For example, the Unified Medical Language System (UMLS) contains millions of entities with their synonyms and defines hundreds of relations among entities. Leveraging this knowledge can benefit a variety of downstream tasks such as named entity recognition and relation extraction. To this end, we propose KeBioLM, a biomedical pretrained language model that explicitly leverages knowledge from the UMLS knowledge bases. Specifically, we extract entities from PubMed abstracts and link them to UMLS. We then train a knowledge-aware language model that firstly applies a text-only encoding layer to learn entity representation and applies a text-entity fusion encoding to aggregate entity representation. Besides, we add two training objectives as entity detection and entity linking. Experiments on the named entity recognition and relation extraction from the BLURB benchmark demonstrate the effectiveness of our approach. Further analysis on a collected probing dataset shows that our model has better ability to model medical knowledge.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

GanjinZero/KeBioLM officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Entity LinkingLanguage ModelingLanguage ModellingNamed Entity RecognitionNamed Entity Recognition (NER)Relation Extractionnamed-entity-recognition

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Named Entity Recognition (NER) BC2GM KeBioLM F1 85.1 #9 of 13 Archive leaderboard report
Named Entity Recognition (NER) BC5CDR-chemical KeBioLM F1 93.3 #11 of 13 Archive leaderboard report
Named Entity Recognition (NER) BC5CDR-disease KeBioLM F1 86.1 #6 of 10 Archive leaderboard report
Named Entity Recognition (NER) JNLPBA KeBioLM F1 82.0 #1 of 17 Archive leaderboard report
Named Entity Recognition (NER) NCBI-disease KeBioLM F1 89.1 #6 of 26 Archive leaderboard report
Relation Extraction ChemProt KeBioLM F1 77.5 #5 of 13 Archive leaderboard report
Relation Extraction DDI KeBioLM F1 81.9 #2 of 3 Archive leaderboard report
Relation Extraction GAD KeBioLM F1 84.3 #2 of 3 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections