Benoît Habert

Symbolic word clustering for medium-size corpora

When trying to identify essential concepts and relationships in a medium-size corpus, it is not always possible to rely on statistical methods, as the frequencies are too low. We present an alternative method, symbolic, based on the simplification of parse trees. We discuss the results on nominal phrases of two technical corpora, analyzed by two different robust parsers used for terminology updating in an industrial company. We compare our results with Hindles scores of similarity.

Elementary dependency trees for identifying corpus-specific semantic classes

Elementary dependency relationships between words within parse trees produced by robust analyzers on a corpus help automate the discovery of semantic classes relevant for the underlying domain. We introduce two methods for extracting elementary syntactic dependencies from normalized parse trees. The groupings which are obtained help identify coarse-grain semantic categories and isolate lexical idiosyncrasies belonging to a specific sublanguage. A comparison shows a satisfactory overlapping with an existing nomenclature for medical language processing. This symbolic approach is efficient on medium size corpora which resist to statistical clustering methods but seems more appropriate for specialized texts.