Rozhkov, Yu.
(2023).
Linguocognitive approach to extracting terms from a corpus of veterinary texts.
International Journal of Philology,
14(4),
46-55.
https://doi.org/10.31548/philolog14(4).2023.05
This research delves into the intricate landscape of computational linguistics with a focused exploration of term identification challenges within the domain of veterinary medicine. A comprehensive analysis was conducted, balancing the difficulties associated with the automated extraction of single-word terms and the structured patterns observed in two-word terms within veterinary dictionaries and scientific literature. The study commenced with a meticulous manual identification of 462 single-word terms, emphasizing the inherent challenges in automating the extraction of terms characterized by linguistic diversity and potential ambiguity. Simultaneously, the investigation of two-word terms unveiled structured patterns, particularly in dictionaries, offering contrasting simplicity for identification through conventional frequency-based methods. The chosen text type, a veterinary dictionary, revealed its own intricacies with a standardized template governing entry construction. The revelation that only 59% of terms find placement in the title section underscored the need for adaptive extraction methods attuned to the varied distribution of terms within dictionary structures. Scientific texts further complicated the term identification landscape by showcasing varying term frequencies, prompting a critical evaluation of standard lexeme selection methods. Building on these insights, the research proposes strategies for refining automated term identification processes. This includes leveraging advanced natural language processing techniques for single-word terms and advocating for adaptive extraction methods for dictionaries, while also proposing a hybrid approach for scientific texts. The interdisciplinary nature of the research is underscored by the recognition of collaboration between linguists, computational scientists, and domain experts as crucial for developing sophisticated models and ontologies that accurately capture the unique linguistic nuances of veterinary medicine. As the digital landscape evolves, this research not only contributes to the advancement of computational linguistic methodologies but also envisions the creation of terminological resources reflecting the dynamic nature of language within the veterinary domain. Through a comprehensive exploration of challenges and opportunities, this research aspires to pave the way for more accurate and adaptable automated systems, offering implications for the broader field of computational linguistics
corpus; corpus analysis; frequency analysis; veterinary terminology; cognitive science
[1] Abraham-Barna, C.G. (2011). Creating a French-Romanian bilingual terminology of veterinary parasitology. Bulletin UASVM Horticulture, 68(2), 87-95.
[2] Baker, M. (2015). Corpora in translation studies: An overview and some suggestions for future research. Target: International Journal of Translation Studies, 7(2), 223-243.
[3] Baker, P. (2019). Glossary of corpus linguistics. Edinburgh: Edinburgh University Press.
[4] Biber, D. (2012). Corpus-based and corpus-driven analyses of language variation and use. In The Oxford handbook of linguistic analysis. Oxford University Press.
[5] Biber, D. (2018). Corpus linguistics: Investigating language structure and use. Cambridge University Press.
[6] Bowker, L. (2016). Towards a corpus-based approach to terminography. Terminology: International Journal of Theoretical and Applied Issues in Specialized Communication, 3(1), 27-52.
[7] Geeraerts, D. (2011). Introduction: Prospects and problems of prototype theory. Linguistics, 27(4), 587-612.
[8] Gonzales, M.C. (2022). Variation in Spanish accounting terminology implications for translators. Terminology, 28(1), 65-102.
[9] McFarland, C. (2013). Veterinary Dictionary and Horseman’s Guide. Phoenix: Western Horseman.
[10] Oostdijk, N. (2010). A corpus linguistic approach to linguistic variation. Literary and Linguistic Computing, 3(1), 12-25.
[11] Oostdijk, N. (2021). Corpus linguistics and the automatic analysis of English. Amsterdam: Rodopi.
[12] Perkhach, R. (2015). Application of computer technologies in the study of medical terminology. Lviv: Lviv Polytechnic Publishing, 186-188.
[13] Perkhach, R.Yu. (2017). Corpus of instructions for medical drugs as a method of studying medical terminology. Philological Studies: Scientific Bulletin of Kryvyi Rih State Pedagogical University, 13, 171-175.
[14] Rozhkov, Yu., & Syrotin, O. (2022). Verbalization of the concepts of disease and animal disease in English. Cogito Multidisciplinary Research Journal, 13(4), 224-233.
[15] Wiebe, J. (2010). Learning subjective adjectives from corpora. New-Mexico State University, 20(4), 54-70.
[16] Zhabotynska, S.A. (2013). Cognitive linguistics: Principles of cognitive modeling. Linguistic Studies, 3-11. Cherkasy: Siach.
[17] Zhabotynska, S.A. (2014). A name as a text: Conceptual network of logical meaning (Analysis of emotion names). Cognition, Communication, Discourse, 6, 47-76.
[18] Zhabotynska, S.A. (2015). Conceptual language analysis: Frame networks. Language: A Scientific-Theoretical Journal of Linguistics, 9, 81-92.
[19] Zhukovska, V.V. (2013). Introduction to corpus linguistics: A textbook. Zhytomyr: Ivan Franko Zhytomyr State University Publishing.