CoRTEx: Contrastive Learning for Representing Terms via Explanations with Applications on Constructing Biomedical Knowledge Graphs
This work addresses the challenge of term clustering for biomedical knowledge graphs, offering a scalable solution that enhances accuracy and generalization beyond existing datasets, though it is incremental by building on contrastive learning with LLM integration.
The paper tackled the problem of clustering synonymous biomedical terms for constructing knowledge graphs, proposing CoRTEx, which uses contrastive learning with LLM-generated explanations to improve term representations, resulting in the highest F1 scores on test sets and clustering over 35 million terms into 22 million clusters with efficient ChatGPT queries.
Objective: Biomedical Knowledge Graphs play a pivotal role in various biomedical research domains. Concurrently, term clustering emerges as a crucial step in constructing these knowledge graphs, aiming to identify synonymous terms. Due to a lack of knowledge, previous contrastive learning models trained with Unified Medical Language System (UMLS) synonyms struggle at clustering difficult terms and do not generalize well beyond UMLS terms. In this work, we leverage the world knowledge from Large Language Models (LLMs) and propose Contrastive Learning for Representing Terms via Explanations (CoRTEx) to enhance term representation and significantly improves term clustering. Materials and Methods: The model training involves generating explanations for a cleaned subset of UMLS terms using ChatGPT. We employ contrastive learning, considering term and explanation embeddings simultaneously, and progressively introduce hard negative samples. Additionally, a ChatGPT-assisted BIRCH algorithm is designed for efficient clustering of a new ontology. Results: We established a clustering test set and a hard negative test set, where our model consistently achieves the highest F1 score. With CoRTEx embeddings and the modified BIRCH algorithm, we grouped 35,580,932 terms from the Biomedical Informatics Ontology System (BIOS) into 22,104,559 clusters with O(N) queries to ChatGPT. Case studies highlight the model's efficacy in handling challenging samples, aided by information from explanations. Conclusion: By aligning terms to their explanations, CoRTEx demonstrates superior accuracy over benchmark models and robustness beyond its training set, and it is suitable for clustering terms for large-scale biomedical ontologies.