Everything transformers: Recognition, classification and normalisation of professions and family relations
Visualitza/Obre
Estadístiques de LA Referencia / Recolecta
Inclou dades d'ús des de 2022
Cita com:
hdl:2117/355557
Tipus de documentText en actes de congrés
Data publicació2021
EditorCEUR-WS.org
Condicions d'accésAccés obert
Llevat que s'hi indiqui el contrari, els
continguts d'aquesta obra estan subjectes a la llicència de Creative Commons
:
Reconeixement 4.0 Internacional
ProjecteANALISIS DE TEXTO MEDICO PARA LA ASSISTENCIA A LA PREDICCION DE DIAGNOSIS (AEI-PID2019-106942RB-C33)
Abstract
This document describes the system submitted by TALP team for IberLEF 2021’s MEDDOPROF Shared Task. The joint occupation mention identification and family relation classification model is composed of a pre-trained DistilBERT architecture followed by a Bidirectional LSTM layer. Occupation normalisation uses Sentence-BERT pre-trained for Semantic Text Similarity (STS) to map the ESCO and SNOMED-CT categories as well as the mentions of occupations from the documents to a vectorial space. K-nearest neighbours is then used to find the most likely category assignments.
CitacióMedina, S.; Turmo, J. Everything transformers: Recognition, classification and normalisation of professions and family relations. A: Iberian Languages Evaluation Forum. "Proceedings of the Iberian Languages Evaluation Forum (IberLEF 2021): co-located with the Conference of the Spanish Society for Natural Language Processing (SEPLN 2021), XXXVII International Conference of the Spanish Society for Natural Language Processing: Málaga, Spain, September, 2021". CEUR-WS.org, 2021, p. 770-775. ISSN 1613-0073.
ISSN1613-0073
Versió de l'editorhttp://ceur-ws.org/Vol-2943/meddoprof_paper4.pdf
Fitxers | Descripció | Mida | Format | Visualitza |
---|---|---|---|---|
meddoprof.2021.pdf | 492,6Kb | Visualitza/Obre |