David Carreto Fidalgo


2021

pdf bib
System description for ProfNER - SMMH: Optimized finetuning of a pretrained transformer and word vectors
David Carreto Fidalgo | Daniel Vila-Suero | Francisco Aranda Montes | Ignacio Talavera Cepeda
Proceedings of the Sixth Social Media Mining for Health (#SMM4H) Workshop and Shared Task

This shared task system description depicts two neural network architectures submitted to the ProfNER track, among them the winning system that scored highest in the two sub-tasks 7a and 7b. We present in detail the approach, preprocessing steps and the architectures used to achieve the submitted results, and also provide a GitHub repository to reproduce the scores. The winning system is based on a transformer-based pretrained language model and solves the two sub-tasks simultaneously.