• Publications
  • Influence
Multilingual Central Repository version 3.0
TLDR
The upgrading process of the Multilingual Central Repository is described, which uses WordNet 3.0 as Interlingual-Index (ILI) and the MCR has been enriched with a disparate set of ontologies: Base Concepts, Top Ontology, WordNet Domains and Suggested Upper Merged Ontology. Expand
Automatic De-identification of Medical Texts in Spanish: the MEDDOCAN Track, Corpus, Guidelines, Methods and Evaluation of Results
TLDR
This paper summarizes the settings, data and results of the first shared track on anonymization of medical documents in Spanish, the MEDDOCAN (Medical Document Anonymization) track, which relied on a carefully constructed synthetic corpus of clinical case documents following annotation guidelines for sensitive data based on the analysis of the EU General Data Protection Regulation. Expand
SemEval-2016 Task 2: Interpretable Semantic Textual Similarity
Comunicacio presentada al 10th International Workshop on Semantic Evaluation (SemEval-2016), celebrat els dies 16 i 17 de juny de 2016 a San Diego, California.
PharmaCoNER: Pharmacological Substances, Compounds and proteins Named Entity Recognition track
TLDR
This work organized the first shared task on detecting drug and chemical entities in Spanish medical documents, named PharmaCoNER, and generated annotation guidelines together with a corpus of 1,000 manually annotated clinical case studies to foster the development of new resources for clinical and biomedical text mining systems of Spanish medical data. Expand
Overview of Automatic Clinical Coding: Annotations, Guidelines, and Solutions for non-English Clinical Cases at CodiEsp Track of CLEF eHealth 2020
TLDR
Despite the considerable complexity of this task, which can be viewed as a hierarchical multi-label classification problem using ICD-10 codes as labels and documents as input, participants obtained very promising results, specially for codes that were well covered by the training data. Expand
A Graph-Based Method to Improve WordNet Domains
TLDR
A novel automatic method to propagate domain information through WordNet, allowing us to detect anomalies in the original WND labels and to compare both labellings, showing that the new labelling clearly outperform the original one by a large margin. Expand
Interpretable Semantic Textual Similarity: Finding and explaining differences between sentences
TLDR
Preliminary evidence that users performed the two tasks better when having access to the explanations is provided, providing preliminary evidence that the dataset and method to automatically produce explanations do help users understand the output of STS systems better. Expand
UBC: Cubes for English Semantic Textual Similarity and Supervised Approaches for Interpretable STS
TLDR
This work presents a system which relies on several resources for token-to-token and phrase- to-phrase similarity to build a data-structure which holds all the information, and then combine the information to get a similarity score. Expand
Predicting the Evolution of COVID-19 Mortality Risk: a Recurrent Neural Network Approach
TLDR
The feasibility of the approach to predict the clinical outcome of patients infected with SARS-CoV-2 has been shown, with the best two RNN ensemble models outperform a Support Vector Classifier and Random Forest and achieving better results than baselines showing system's ability towards early predictions. Expand
A proposal for improving WordNet Domains
TLDR
This paper presents a novel semi-automatic method to propagate domain information through the MCR allowing for cross-checking the content of the Multilingual Central Repository (MCR) and comparing both labellings allowing for detecting anomalies in the original WND labels. Expand
...
1
2
3
...