Computational Tool for Automatic Term Extraction - ATEM

Abstract

Automatic term extraction enables the identification of the most representative terms within a corpus through computational processes. This process facilitates the creation of lexicographic materials or common databases, which are pivotal for knowledge acquisition in science as they help eliminate ambiguity in definitions pertaining to a specific domain. Specialized literature highlights the need for a common foundation on best practices for the Internet of Things (IoT) to consolidate knowledge and adapt new working methods. However, the manual creation of terminological resources is inefficient, does not keep pace with the rapid evolution of subjects, and is both time-consuming and costly. This article introduces ATEM, a term extraction tool for web and mobile environments that incorporates a hybrid method for identifying relevant terms in English-language scientific literature on IoT. ATEM is developed using a Service-Oriented Architecture (SOA) and employs programming languages such as JavaScript and Python. It also uses tools like the Flask framework and NLP-specific libraries such as NLTK and SpaCy. The computational tool includes the CValue algorithm, along with statistical and linguistic techniques in several steps: (i) corpus reception; (ii) text preprocessing; (iii) stop-word removal; (iv) Part-of-Speech (POS) tagging; and (v) filtering through linguistic and statistical rules. This results in a list of potential terms and a weight indicating their relevance within the corpus. The method was tested on five corpora from different domains, and ATEM processes and retrieves terms with 75% precision and 89% recall, highlighting its versatility across corpora. According to the tests, ATEM supports terminological extraction from IoT literature. It contributes to: (i) the development of lexicographic resources; (ii) language translation; and (iii) the creation of shared databases.