Skip to main navigation Skip to search Skip to main content

Using pseudo-synonyms to generate embeddings for clinical terms

  • Western Sydney University

Research output: Chapter in Book / Conference PaperChapterpeer-review

1 Citation (Scopus)

Abstract

Existing approaches attempt to explicitly learn clinical term embedding from clinical datasets by training a model, such as word2vec and recurrent neural network or fine-tuning a pre-trained large language model (LLM). While the corpus-based methods require exposure to a rich vocabulary in the training corpus, insufficient contextual information, in clinical terms, makes LLMs prone to failure to generate meaningful embeddings. In this regard, we propose a novel method to generate embeddings for clinical terms using pseudo-synonyms - terms that might be associated with a clinical term but not the exact synonyms. The proposed method uses an LLM as a black-box tool and requires no training or fine-tuning. To demonstrate the effectiveness of the learned embeddings, we compared our approach with existing corpus-based embedding approaches on semantic textual similarity (STS) tasks on five benchmark datasets. Our proposed method outperformed all existing approaches (https://github.com/Xujan24/pseudo-synonyms-for-clinical-term-embedding).

Original languageEnglish
Title of host publicationData Science: Foundations and Applications: 29th Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD 2025, Sydney, Australia, June 10-13, 2025, Proceedings, Part VII
EditorsXintao Wu, Myra Spiliopoulou, Can Wang, Vipin Kumar, Longbing Cao, Xiangmin Zhou, Guansong Pang, Joao Gama
Place of PublicationSingapore
PublisherSpringer
Pages209-220
Number of pages12
ISBN (Electronic)9789819682980
ISBN (Print)9789819682973
DOIs
Publication statusPublished - 2025
Event29th Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD 2025 - Sydney, Australia
Duration: 10 Jun 202513 Jun 2025

Publication series

NameLecture Notes in Computer Science
Volume15876
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference29th Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD 2025
Country/TerritoryAustralia
CitySydney
Period10/06/2513/06/25

Keywords

  • Clinical Term Embedding
  • Large Language Models
  • Semantic Textual Similarity

Fingerprint

Dive into the research topics of 'Using pseudo-synonyms to generate embeddings for clinical terms'. Together they form a unique fingerprint.

Cite this