Training and intrinsic evaluation of lightweight word embeddings for the clinical domain in Spanish.

Autor:	Chiu C; Department of Mathematical Engineering, FCFM, Universidad de Chile, Santiago, Chile., Villena F; Center for Mathematical Modeling & CNRS IRL2807, FCFM, Universidad de Chile, Santiago, Chile.; Department of Computer Sciences, FCFM, University of Chile, Santiago, Chile., Martin K; Department of Computer Sciences, Massachusetts Institute of Technology, Cambridge, MA, United States., Núñez F; Center for Mathematical Modeling & CNRS IRL2807, FCFM, Universidad de Chile, Santiago, Chile.; Department of Language Sciences, Pontificia Universidad Católica de Chile, Santiago, Chile., Besa C; Department of Radiology, School of Medicine, Pontificia Universidad Católica de Chile, Santiago, Chile.; Millenium Institute for Intelligent Healthcare Engineering, ANID, Santiago, Chile., Dunstan J; Center for Mathematical Modeling & CNRS IRL2807, FCFM, Universidad de Chile, Santiago, Chile.; Millenium Institute for Intelligent Healthcare Engineering, ANID, Santiago, Chile.; Initiative for Data & Artificial Intelligence, FCFM, University of Chile, Santiago, Chile.
Jazyk:	angličtina
Zdroj:	Frontiers in artificial intelligence [Front Artif Intell] 2022 Sep 21; Vol. 5, pp. 970517. Date of Electronic Publication: 2022 Sep 21 (Print Publication: 2022).
DOI:	10.3389/frai.2022.970517
Abstrakt:	Resources for Natural Language Processing (NLP) are less numerous for languages different from English. In the clinical domain, where these resources are vital for obtaining new knowledge about human health and diseases, creating new resources for the Spanish language is imperative. One of the most common approaches in NLP is word embeddings, which are dense vector representations of a word, considering the word's context. This vector representation is usually the first step in various NLP tasks, such as text classification or information extraction. Therefore, in order to enrich Spanish language NLP tools, we built a Spanish clinical corpus from waiting list diagnostic suspicions, a biomedical corpus from medical journals, and term sequences sampled from the Unified Medical Language System (UMLS). These three corpora can be used to compute word embeddings models from scratch using Word2vec and fastText algorithms. Furthermore, to validate the quality of the calculated embeddings, we adapted several evaluation datasets in English, including some tests that have not been used in Spanish to the best of our knowledge. These translations were validated by two bilingual clinicians following an ad hoc validation standard for the translation. Even though contextualized word embeddings nowadays receive enormous attention, their calculation and deployment require specialized hardware and giant training corpora. Our static embeddings can be used in clinical applications with limited computational resources. The validation of the intrinsic test we present here can help groups working on static and contextualized word embeddings. We are releasing the training corpus and the embeddings within this publication. Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest. (Copyright © 2022 Chiu, Villena, Martin, Núñez, Besa and Dunstan.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu