RIMAX: Ranking Semantic Rhymes by calculating Definition Similarity
This addresses a domain-specific problem for computational linguistics and poetry analysis, but it appears incremental as it applies an existing method to new data.
The paper tackles the problem of detecting semantic rhymes in Mexican Spanish by calculating definition similarity using a Vector Space Model, and preliminary manual evaluation results are very encouraging.
This paper presents RIMAX, a new system for detecting semantic rhymes, using a Comprehensive Mexican Spanish Dictionary (DEM) and its Rhyming Dictionary (REM). We use the Vector Space Model to calculate the similarity of the definition of a query with the definitions corresponding to the assonant and consonant rhymes of the query. The preliminary results using a manual evaluation are very encouraging.