Pointwise Mutual Information

A statistical measure used in natural language processing to quantify the strength of association between two words based on how much more frequently they co-occur in a corpus than would be expected by chance. PMI is calculated as the logarithm of the ratio of the observed co-occurrence probability to the product of the individual word probabilities. In accessibility applications, PMI is used to build semantic knowledge bases for word prediction systems, helping identify words that are genuinely related in meaning (such as "school" and "teacher") rather than merely frequent, which improves the contextual relevance of predictions offered to users with disabilities.