ITEXT-BIO: Intelligent Term EXTraction for BIOmedical analysis

Abstract

Here, we introduce ITEXT-BIO, an intelligent process for biomedical domain terminology extraction from textual documents and subsequent analysis. The proposed methodology consists of two complementary approaches, including free and driven term extraction. The first is based on term extraction with statistical measures, while the second considers morphosyntactic variation rules to extract term variants from the corpus. The combination of two term extraction and analysis strategies is the keystone of ITEXT-BIO. These include combined intra-corpus strategies that enable term extraction and analysis either from a single corpus (intra), or from corpora (inter). We assessed the two approaches, the corpus or corpora to be analysed and the type of statistical measures used. Our experimental findings revealed that the proposed methodology could be used: (1) to efficiently extract representative, discriminant and new terms from a given corpus or corpora, and (2) to provide quantitative and qualitative analyses on these terms regarding the study domain.

Approaches, tools, algorithms, and methods for automatic term extraction: A systematic literature mapping

“…According to the review, one of the most commonly used algorithms is C-Value, which handles a hybrid approach and uses the frequency of occurrence and nesting of candidate terms to determine the relevant ones depending on the domain. The authors agree that the algorithm's potential lies in its hybrid characteristic because one part is in charge of applying statistical methods, and subsequently, linguistic filters are applied (Lahbib et al 2015;Bakar et al 2015;Ali and Saad 2016;Du et al 2016;Benabdallah et al 2017;Arora et al 2017;Mykowiecka et al 2018;Kafando et al 2021).…”

“…On the other hand, the Term Frequency-Inverse Document Frequency (TF-IDF) algorithm applies weighting methods to express the level of relevance of a candidate term within a text. It is an algorithm used for term extraction, and although there are many systems with different variations, the basis is still TF-IDF (Guo et al 2015;Ali and Saad 2016;Abduljabbar et al 2018;Afrizal et al 2019;Kafando et al 2021).…”

Proceedings of the 19th Workshop on Multiword Expressions (MWE 2023)

“…While many strategies for identifying MWEs have been presented in the past (Ramisch et al, 2010;Kafando et al, 2021;, we found that applying them to the medical domain (and especially its clinical counterpart) was challenging due to the extreme corpus size that would be required to produce statistically significant results for the long tail of medical entities.…”

Detecting Idiomatic Multiword Expressions in Clinical Terminology using Definition-Based Representation Learning

“…While many strategies for identifying MWEs have been presented in the past (Ramisch et al, 2010;Kafando et al, 2021;Zeng and Bhat, 2021), we found that applying them to the medical domain (and especially its clinical counterpart) was challenging due to the extreme corpus size that would be required to produce statistically significant results for the long tail of medical entities.…”