Building Croatian Medical Dictionary from Medical Corpus

Scientific paper - Preliminary note / Short communication

• Title (croatian): Izrada hrvatskoga medicinskog rječnika iz medicinskoga korpusa
• Author: Kristina Kocijan https://orcid.org/0000-0001-9467-5313
• Author: Silvia Kurolt
• Author: Linda Mijić
• Author's institution: University of Zadar; (Department of Classical Philology)
• Author's institution: University of Zagreb; Faculty of Humanities and Social Sciences; (Department of information and Communication sciences)
• Scientific / art field, discipline and subdiscipline: SOCIAL SCIENCES; Information and Communication Sciences

Abstract (english)

The overall objective of this project is to define linguistic models at the lexical and syntactic levels that appear in the health domain, depending on the type of corpus. In the first phase of the project, the texts forming the medical corpus A – MedCorA (2,232 pharmaceutical instructions for medicaments available in Croatia) were prepared. The terminology found in this corpus was analyzed and the semantic subdomains (anatomy, condition, microorganism, chemistry, etc.) within the medical domain were defined and added to the dictionary entries. These dictionary resources were used as the foundation for the second phase in which NooJ morphological grammars were built allowing annotation of medical terminology in the corpus. Said grammars were built to allow for recognizing Latinisms, as well as Latin expressions written with Croatian case endings, not only Croatian words. Prepared resources are made available to a broader scientific community via Sketch Engine for further research in the field of medicine enabling additional research and development of algorithms for, among others, medical documents classification, medical texts’ information retrieval or machine translation of medical documentation, taking into account quality and reliability as well as terminology variability.

Abstract (croatian)

Osnovni je cilj ovoga projekta definiranje leksičkih i sintaktičkih jezičnih modela koji se pojavljuju u području medicine, a ovisno o vrsti korpusa. U prvoj fazi projekta prikupljeni su tekstovi koji čine medicinski korpus A – MedCorA (2232 farmaceutske upute za lijekove dostupne u Hrvatskoj). Nazivlje je iz korpusa analizirano, a potom su definirane semantičke poddomene (anatomija, stanja, mikroorganizmi, kemija itd.) unutar medicinske domene. Semantičke su oznake dodane u rječnik, gdje su poslužile kao osnova za drugu fazu projekta u kojoj su izrađene i NooJ morfološke gramatike za prepoznavanje i označavanje latinizama kao i latinskih izraza koji se koriste hrvatskim padežnim nastavcima.
Pripremljeni resursi stavljaju se na raspolaganje široj znanstvenoj zajednici putem SketchEnginea za daljnja istraživanja u području obrade jezika i medicine, omogućujući pritom nova istraživanja i razvoj algoritama za, među ostalim, klasifikaciju medicinskih dokumenata, pronalaženje podataka u medicinskim tekstovima, prevođenje medicinske dokumentacije, a uzimajući u obzir kvalitetu i pouzdanost podataka, ali i terminološku varijabilnost.

• Keywords (english): language processing; semantic annotations; medical domain; NooJ; Croatian
• Keywords (croatian): obrada jezika; semantičke oznake; medicinska domena; NooJ; hrvatski jezik
• Language: english
• Publication type: Scientific paper - Preliminary note / Short communication
• Publication status: Published
• Peer review: Peer review
• Publication version: Published version
• Journal title: Rasprave: Časopis Instituta za hrvatski jezik i jezikoslovlje
• Numbering: vol. 46, no. 2, pp. 765-782
• p-ISSN: 1331-6745
• e-ISSN: 1849-0379
• DOI: https://doi.org/10.31724/rihjj.46.2.17
• URN:NBN: urn:nbn:hr:131:854666
• Publication: 2020
• Document URL: https://hrcak.srce.hr/245468
• Type of resource: Text
• Access conditions: Open access
• Created on: 2020-11-07 00:18:09