Papers by Pilar López Úbeda
SHARE: A Lexicon of Harmful Expressions by Spanish Speakers (2022.lrec-1)
Copied to clipboard
Flor Miriam Plaza-del-Arco, Ana Belén Parras Portillo, Pilar López Úbeda, Beatriz Gil, María-Teresa Martín-Valdivia
| Challenge: | Using natural language processing, offensive comments can be created by composition of words. |
| Approach: | They propose to use a lexical resource with 10,125 offensive terms and expressions collected from Spanish speakers to retrieve the vocabulary. |
| Outcome: | The proposed resource has 10,125 offensive terms and expressions and is used to identify spans in Spanish. |
Using Snomed to recognize and index chemical and drug mentions. (D19-57)
Copied to clipboard
| Challenge: | a new named entity extraction system is proposed for biological texts . the system is based on machine learning and deep learning . |
| Approach: | They propose a named entity extraction system based on machine learning and deep learning . they propose to map drug names in Spanish biomedical texts using Snomed . |
| Outcome: | The proposed system achieves 78% in the first sub-track and 72% in the second task. |