The semantic similarity function allows to calculate the semantic distance between any pair of words present in an LSA-based space, using a general-purpose Spanish corpus of Wikipedia texts.
The lists can be copied and pasted directly from other programs such as Microsoft Excel, even selecting cells through different columns.
The application automatically removes spaces, paragraph breaks, periods, commas, etc. before performing the search.
The program is not case sensitive. However, it distinguishes the accented words from those without a graphic accent.
It does not accept numbers or characters not present in words (e.g.: %, #, $). In case any of these symbols are introduced, they will be eliminated.
LSA Semantic similarity
For details of the semantic space explored here, see (and cite):
- Article in preparation -