Papers by Bernal Gutierrez
Solving the Right Problem is Key for Translational NLP: A Case Study in UMLS Vocabulary Insertion (2023.findings-emnlp)
Copied to clipboard
| Challenge: | a gap exists between research output and real-world task for automated NLP systems . a recent study shows that powerful models alone will not yield translational NLP solutions . |
| Approach: | They propose a formulation for UMLS vocabulary insertion which mirrors the real-world task . they propose measurable qualitative improvements to editors who carry out the UVI task based on strong datasets . |
| Outcome: | The proposed model outperforms existing models and improves the UVI task. |