Biomedical term extraction: overview and a new methodology

• DOI: 10.1007/s10791-015-9262-2
• Publication Date: 2015-08-24T02:20:40Z
• Authors: Juan Antonio Loss...; Clement Jonquet; Mathieu Roche; Maguelonne Teisseire
• Keywords: BioNLP; recherche de l'information; Text Mining; 02 engineering and technology; Biomedical Terminology Extraction; ACM: I.: Computing Methodologies/I.2: ARTIFICIAL INTELLIGENCE/I.2.7: Natural Language Processing; [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]; ACM: H.: Information Systems/H.3: INFORMATION STORAGE AND RETRIEVAL/H.3.3: Information Search and Retrieval; http://aims.fao.org/aos/agrovoc/c_24907; terminologie; méthode statistique; Automatic Term Extraction; 0202 electrical engineering, electronic engineering, information engineering; ACM: I.: Computing Methodologies/I.2: ARTIFICIAL INTELLIGENCE/I.2.7: Natural Language Processing/I.2.7.6: Text analysis; http://aims.fao.org/aos/agrovoc/c_3863; ACM: I.: Computing Methodologies/I.5: PATTERN RECOGNITION/I.5.4: Applications/I.5.4.2: Text processing; Natural Language Processing; U10 - Informatique, mathématiques et statistiques; [INFO.INFO-WB]Computer Science [cs]/Web; 006; ACM: I.: Computing Methodologies/I.2: ARTIFICIAL INTELLIGENCE/I.2.7: Natural Language Processing/I.2.7.1: Language generation; méthodologie; Web Mining; [INFO.INFO-TT]Computer Science [cs]/Document and Text Processing; C30 - Documentation et information; [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR]; extraction; [INFO.INFO-BI]Computer Science [cs]/Bioinformatics [q-bio.QM]; http://aims.fao.org/aos/agrovoc/c_12522; Graphs; http://aims.fao.org/aos/agrovoc/c_7377; http://aims.fao.org/aos/agrovoc/c_36910

Terminology extraction is an essential task in domain knowledge acquisition, as well as for information retrieval. It is also a mandatory first step aimed at building/enriching terminologies and ontologies. As often proposed in the literature, existing terminology extraction methods feature linguistic and statistical aspects and solve some problems related (but not completely) to term extraction, e.g. noise, silence, low frequency, large-corpora, complexity of the multi-word term extraction process. In contrast, we propose a cutting edge methodology to extract and to rank biomedical terms, covering all the mentioned problems. This methodology offers several measures based on linguistic, statistical, graphic and web aspects. These measures extract and rank candidate terms with excellent precision: we demonstrate that they outperform previously reported precision results for automatic term extraction, and work with different languages (English, French, and Spanish). We also demonstrate how the use of graphs and the web to assess the significance of a term candidate, enables us to outperform precision results. We evaluated our methodology on the biomedical GENIA and LabTestsOnline corpora and compared it with previously reported measures.