Previous abstract | Contents | Next abstract

Learning from Parsed Sentences with INTHELEX

In the context of language learning, we address a logical approach to information extraction. The system INTHELEX, used to carry out this task, requires a logic representation of sentences to run the learning algorithm. Hence, the need for parsers to produce structured representations from raw text. This led us to develop a prototypical Italian language parser, as a pre-processor in order to obtain the structured representation of sentences required for the symbolic learner to work. A preliminary experimentation proved that the logic approach to learning from language is able to capture the semantics underlying the kind of sentences that were processed, even if a comparison with classical methods as regards efficiency has still to be done.


F. Esposito, S. Ferilli, N. Fanizzi and G. Semeraro, Learning from Parsed Sentences with INTHELEX. In: Proceedings of CoNLL-2000 and LLL-2000, Lisbon, Portugal, 2000. [ps] [pdf] [bibtex]
Last update: June 27, 2001. erikt@uia.ua.ac.be