2023
MedCPT: Contrastive Pre-trained Transformers with large-scale PubMed search logs for zero-shot biomedical information retrieval
Jin Q, Kim W, Chen Q, Comeau D, Yeganova L, Wilbur W, Lu Z. MedCPT: Contrastive Pre-trained Transformers with large-scale PubMed search logs for zero-shot biomedical information retrieval. Bioinformatics 2023, 39: btad651. PMID: 37930897, PMCID: PMC10627406, DOI: 10.1093/bioinformatics/btad651.Peer-Reviewed Original ResearchConceptsInformation retrievalIR tasksUser click logsSemantic information retrievalBiomedical information retrievalBiomedical knowledge acquisitionPre-trained TransformerClinical decision supportClick logsSearch logsContrastive learningLexical matchingArt performanceIR systemsSemantic retrievalBiomedical articlesDecision supportSentence representationModel encoderKnowledge acquisitionLarge modelsSemantic evaluationRetrievalTransformer modelUnprecedented scale
2019
BioSentVec: creating sentence embeddings for biomedical texts
Chen Q, Peng Y, Lu Z. BioSentVec: creating sentence embeddings for biomedical texts. 2019, 00: 1-5. DOI: 10.1109/ichi.2019.8904728.Peer-Reviewed Original ResearchNatural language processing systemsSentence embeddingsBiomedical textAdvanced deep learning methodsDeep learning methodsBiomedical text miningBiomedical word embeddingsLanguage processing systemPre-trained sentence encodersText miningArt performanceLearning methodsSentence semanticsSentence encoderWord embeddingsProcessing systemBenchmarking resultsEmbeddingSimilarity taskClinical notesTaskEssential partGeneral domainsClinical databaseSemantics