Weighted Co-Occurrence Bio-term Graph for Unsupervised Word Sense Disambiguation in the Biomedical Domain

• Main Authors: Jia, Y. (Author), Papadopoulou, M. (Author), Roche, C. (Author), Zhang, X. (Author), Zhang, Z. (Author)
• Format: Article
• Language: English
• Published: Institute of Electrical and Electronics Engineers Inc. 2023
• Subjects: Biological system modeling; Biomedical informatics; Biomedical Natural language processing; Bit error rate; Natural language processing; Neural networks; Personalised PageRank algorithm; Task analysis; Transformers; Unified medical language system; Unified modeling language; Word sense disambiguation
• Online Access: View Fulltext in Publisher; View in Scopus

 Word Sense Disambiguation (WSD) is a significant and challenging task for text understanding and processing. This paper presents an unsupervised approach based on weighted co-occurrence bio-term graph (WCOTG) for performing WSD in the biomedical domain. The graph is automatically created from biomedical terms that are extracted from a corpus of downloaded scientific abstracts. Two kinds of weights are introduced on the links of the built bio-term graph and are taken as important factors in the process of disambiguation. The modified Personalised PageRank (PPR) algorithm is used for performing WSD. When evaluated on the NLM-WSD and MSH-WSD1 test datasets, and an acronym test set, the method outperforms the widely used unsupervised ones addressing the same problem, and the average result is almost equal to that of the BlueBERT_LE2-based method. In contrast, our method has no additional enhancement or training for BERT3-based models. Comparative experiments validate the positive effect of links’ weight on disambiguation efficiency. Last, the statistical experiments on the relation among system accuracy, numbers of medical abstracts in the corpus, and the corresponding extracted terms suggest an excellent minimum corpus scale when resources are limited. Author