Semantic distance

A computational measure of how different two words are in meaning, typically derived from word embedding models like word2vec that represent words as vectors in a high-dimensional space. In caption evaluation for DHH users, semantic distance between an ASR error and the intended word predicts comprehension impact: substituting "kitchen" with "kitten" (large semantic distance) causes greater confusion than "kitchen" with "cookroom" (small semantic distance), even though both are single-word errors.