Building a medical Spanish lexicon

Area of Science:

• Computational linguistics
• Medical informatics
• Natural Language Processing (NLP)

Background:

• Development of specialized lexicons is crucial for accurate medical NLP.
• Existing resources for Spanish medical language processing are limited.
• The SPECIALST English lexicon provides a foundational structure for lexical development.

Purpose of the Study:

• To create a freely available Spanish medical syntactic lexicon.
• To facilitate automated processing of Spanish clinical text.
• To support research in Spanish medical NLP.

Main Methods:

• Initial population using a bilingual medical term list.
• Corpus-based term discovery for comprehensive coverage.
• Simplification of the SPECIALST English lexicon structure for lexical records.
• Development of tools for lexical variant generation and normalization.

Main Results:

• A foundational Spanish medical syntactic lexicon is under development.
• The lexicon will include normalized terms and their variants.
• Associated tools for variant generation and normalization will be provided.

Conclusions:

• The lexicon will enhance Spanish medical NLP capabilities.
• Free availability promotes wider adoption and research.
• The project addresses a gap in Spanish biomedical language resources.