Search Results for author: Koldo Gojenola

Found 13 papers, 0 papers with code

Explanatory Argument Extraction of Correct Answers in Resident Medical Exams

no code implementations1 Dec 2023 Iakes Goenaga, Aitziber Atutxa, Koldo Gojenola, Maite Oronoz, Rodrigo Agerri

Comprehensive experimentation with language models for Spanish shows that sometimes multilingual models fare better than monolingual ones, even outperforming models which have been adapted to the medical domain.

Multiple-choice

EriBERTa: A Bilingual Pre-Trained Language Model for Clinical Natural Language Processing

no code implementations12 Jun 2023 Iker de la Iglesia, Aitziber Atutxa, Koldo Gojenola, Ander Barrena

We demonstrate that EriBERTa outperforms previous Spanish language models in the clinical domain, showcasing its superior capabilities in understanding medical texts and extracting meaningful information.

Language Modelling Transfer Learning

IxaMed at PharmacoNER Challenge 2019

no code implementations WS 2019 Xabier Lahuerta, Iakes Goenaga, Koldo Gojenola, Aitziber Atutxa Salazar, Maite Oronoz

In order to identify named entities we have made use of a Bi-LSTM with a CRF on top in combination with different types of word embeddings.

Word Embeddings

Towards discourse annotation and sentiment analysis of the Basque Opinion Corpus

no code implementations WS 2019 Jon Alkorta, Koldo Gojenola, Mikel Iruskieta

Discourse information is crucial for a better understanding of the text structure and it is also necessary to describe which part of an opinionated text is more relevant or to decide how a text span can change the polarity (strengthen or weaken) of other span by means of coherence relations.

Sentiment Analysis

The impact of simple feature engineering in multilingual medical NER

no code implementations WS 2016 Rebecka Weegar, Arantza Casillas, Arantza Diaz de Ilarraza, Maite Oronoz, Alicia P{\'e}rez, Koldo Gojenola

The goal of this paper is to examine the impact of simple feature engineering mechanisms before applying more sophisticated techniques to the task of medical NER.

Feature Engineering Lemmatization +3

Fully unsupervised low-dimensional representation of adverse drug reaction events through distributional semantics

no code implementations WS 2016 Alicia P{\'e}rez, Arantza Casillas, Koldo Gojenola

In brief, the ADRs are represented as vectors that link the drug with the disease in their context through a recursive additive model.

Cannot find the paper you are looking for? You can Submit a new open access paper.