Sense-aware semantic analysis: a multi-prototype word representation model using Wikipedia
Zhaohui Wu, Clyde Lee Giles · 2015
Human languages are naturally ambiguous, which makes it difficult to automatically understand the semantics of text. Most vector space models (VSM) treat all occur-rences of a word as the same and build a single vector to represent the meaning of a word, which fails to cap-ture any ambiguity. We present sense-aware semantic analysis (SaSA), a multi-prototype VSM for word repre-sentation based on Wikipedia, which could account for homonymy and polysemy. The “sense-specific ” proto-types of a word are produced by clustering Wikipedia pages based on both local and global contexts of the word in Wikipedia. Experimental evaluation on semantic relatedness for both isolated words and words in senten-tial contexts and word sense induction demonstrate its effectiveness.