Using Linguistic Structures in Textual Information Extraction
Résumé
Text Mining is about the task of searching useful knowledge in a natural language document.
Given the cost of a (full) morpho-syntactic analysis of a textual database, specially when the linguistic rules are not respected, most text mining techniques process without using the linguistic structure of those documents.
In this paper, we show how the Grammatical Induction can help extract the (partial) structure of the sublanguages used in a text.
We present the practical contribution of the Grammatical Induction by reporting an Information Extraction process applied to a fragmented announcement corpus.