no code implementations • EMNLP (ClinicalNLP) 2020 • Elisa Terumi Rubel Schneider, João Vitor Andrioli de Souza, Julien Knafou, Lucas Emanuel Silva e Oliveira, Jenny Copara, Yohan Bonescki Gumiel, Lucas Ferro Antunes de Oliveira, Emerson Cabrera Paraiso, Douglas Teodoro, Cláudia Maria Cabral Moro Barra
We transfer learned information encoded in a multilingual-BERT model to a corpora of clinical narratives and biomedical-scientific papers in Brazilian Portuguese.
Ranked #1 on Named Entity Recognition (NER) on SemClinBr
no code implementations • EMNLP (WNUT) 2020 • Julien Knafou, Nona Naderi, Jenny Copara, Douglas Teodoro, Patrick Ruch
Recent improvements in machine-reading technologies attracted much attention to automation problems and their possibilities.
no code implementations • SemEval (NAACL) 2022 • Hossein Rouhizadeh, Douglas Teodoro
The goal of this task is to locate and classify named entities in unstructured short complex texts in 11 different languages. After training a variety of contextual language models on the NER dataset, we used an ensemble strategy based on a majority vote to finalize our model.
Multilingual Named Entity Recognition named-entity-recognition +2
no code implementations • 19 Apr 2024 • Anthony Yazdani, Alban Bornet, Boya Zhang, Philipp Khlebnikov, Poorya Amini, Douglas Teodoro
Adverse drug events (ADEs) significantly impact clinical research and public health, contributing to failures in clinical trials and leading to increased healthcare costs.
no code implementations • 15 Aug 2023 • Anthony Yazdani, Hossein Rouhizadeh, David Vicente Alvarez, Douglas Teodoro
This paper outlines the performance evaluation of a system for adverse drug event normalization, developed by the Data Science for Digital Health (DS4DH) group for the Social Media Mining for Health Applications (SMM4H) 2023 shared task 5.
1 code implementation • 8 Feb 2023 • Anthony Yazdani, Dimitrios Proios, Hossein Rouhizadeh, Douglas Teodoro
Current approaches for clinical information extraction are inefficient in terms of computational costs and memory consumption, hindering their application to process large-scale electronic health records (EHRs).
no code implementations • 14 Feb 2022 • Boya Zhang, Nona Naderi, Fernando Jaume-Santero, Douglas Teodoro
The TREC Health Misinformation track focused on the development of retrieval methods that provide relevant, correct and credible information for health related searches on the Web.
1 code implementation • EMNLP 2021 • Sohrab Ferdowsi, Nikolay Borissov, Julien Knafou, Poorya Amini, Douglas Teodoro
We consider the hierarchical representation of documents as graphs and use geometric deep learning to classify them into different categories.
no code implementations • 24 Jul 2020 • Jenny Copara, Nona Naderi, Julien Knafou, Patrick Ruch, Douglas Teodoro
The results show that ensemble of contextualized language models can provide an effective method to extract information from chemical patents.
no code implementations • JEPTALNRECITAL 2020 • Jenny Copara, Julien Knafou, Nona Naderi, Claudia Moro, Patrick Ruch, Douglas Teodoro
Our best approach achieved an F1 -measure of 66{\%} for symptoms and signs, and pathology categories, being top 1 for subtask 1.