How to exploit paralinguistic features to identify acronyms in texts?

• Main Author: Roche, Mathieu
• Other Authors: ADVanced Analytics for data SciencE (ADVANSE), Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier (LIRMM), Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS), Territoires, Environnement, Télédétection et Information Spatiale (UMR TETIS), Centre de Coopération Internationale en Recherche Agronomique pour le Développement (Cirad)-AgroParisTech-Institut national de recherche en sciences et technologies pour l'environnement et l'agriculture (IRSTEA), ANR-12-JS02-0010,SIFR,Indexation sémantique de ressources biomédicales francophones(2012)
• Format: Conference Object
• Language: English
• Published: HAL CCSD 2014
• Subjects: Acronym expansion; Text mining; [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR]; [INFO.INFO-TT]Computer Science [cs]/Document and Text Processing; [INFO.INFO-WB]Computer Science [cs]/Web; [SPI.OTHER]Engineering Sciences [physics]/Other; Iceland
• Online Access: https://hal-lirmm.ccsd.cnrs.fr/lirmm-00974797; https://hal-lirmm.ccsd.cnrs.fr/lirmm-00974797/document; https://hal-lirmm.ccsd.cnrs.fr/lirmm-00974797/file/identification_Acronyms.pdf

International audience This paper addresses the issue of acronym dictionary building. The first step of the process identifies acronym/definition candidates, the second one selects candidates based on a letter alignment method. This approach has two advantages because it enables (1) to annotate documents, (2) to build specific dictionaries. More precisely, this paper discusses the use of a specific linguistic concept, the gloss, in order to identify candidates. The proposed method based on paralinguistic markers is independent of languages.