Machine Learning for the Identification and Classification of Key Phrases from Clinical Documents in Spanish

Abstract

The key phrases play a very important role because they allow us to characterize the content of a text in a short way and even answer questions related to it. Due to the above, the extraction and classification of these words are a competent problem in different areas of knowledge such as Information Retrieval, Natural Language Processing, among others. This research presents a proposed solution for the identification and classification of key phrases through automatic learning algorithms, in electronic documents related to health topics written in Spanish. According to the experimental results, the proposed algorithm achieves 94% of correctly classified key phrases and 72% of precision for the identification phase.