Tools

Evaluation scorer

Italian pre-processing tools

To facilitate the participation to the task, in this section we are making available a set of pointers to state-of-the-art pre-processing tools (e.g. tokenisers, lemmatisers, parts-of-speech taggers, syntactic parsers etc.) freely available for research purposes and which task participants can use to pre-process the FactA datasets. The list is not exhaustive and we encourage participants or interested researchers to contact the organizers to publicise and make available additional pre-processing tools or wrong information.

 Tool Name Levels of analysis available Link
 TextPro v.2.0boilerplate removal (html), tokenization, morphological analysis, lemmatization, part-of-speech tagging, entity recognition and classification, dependency parsing (MaltParser), key-concept extraction http://hlt-services2.fbk.eu/textpro/?page_id=31
 Tanl Italian Pipelinetokenization, morphological analysis, lemmatization, part-of-speech tagging, entity recognition and classification, dependency parsing (DeSR) http://tanl.di.unipi.it/it/overview.html
Turin University Language Environment (TULE)tokenization, morphological analysis, lemmatization, parts-of-speech tagging, dependency parser (based on the Turin University TreeBank) http://www.tule.di.unito.it
 LinguA tokenization, morphological analysis, lemmatization, parts-of-speech tagging, dependency parser http://www.italianlp.it/demo/linguistic-annotation-tool/