Skip to main content
Fig. 5 | BMC Medical Informatics and Decision Making

Fig. 5

From: Combining unsupervised, supervised and rule-based learning: the case of detecting patient allergies in electronic health records

Fig. 5

Transformation of words into vectors in the VSM. In the figure to the left are shown how words are represented as vectors according to contextual (document) frequency. In the table in the middle is shown an example of a word-context matrix (for the sentences “I like machine learning,” “I like NLP,” and “I enjoy programming”) where unique corpus relevant co-occurring words are counted on a global scale. Finally, to the right is shown an example of how closely related words vectors relate to each other in the continuous vector space

Back to article page

BMC Medical Informatics and Decision Making

ISSN: 1472-6947

Contact us