Evaluation of a Semantically Oriented Dependency Grammar for Italian at EVALITA 2009
نویسندگان
چکیده
This paper describes CELI’s participation to the EVALITA 2009 dependency evaluation task, which was based on a symbolic dependency grammar for Italian. The discussion on the results achieved by such a grammar emphasizes the fact that they are obtained by linearizing the CoNLL input and parsing it from scratch, thus generating extra errors due to lexicon look-up and POS tagging. In the final section we provide some explanation of the fact that the scores obtained in the pilot subtask were lower than the ones for the main subtask. Overall, however, the results of the participation prove that a rule approach is viable and sustainable for real life applications.
منابع مشابه
Evalita’09 Parsing Task: constituency parsers and the Penn format for Italian
The aim of Evalita Parsing Task is at defining and extending the state of the art for parsing Italian by encouraging the application of existing models and approaches. Therefore, as in the first edition, the Task includes two tracks, i.e. dependency and constituency. This second track is based on a development set in a format, which is an adaptation for Italian of the Penn Treebank format, and ...
متن کاملThe 2009 UNITN EVALITA Italian Spoken Dialogue System
This report describes the conversational system designed at the University of Trento for the Evalita 2009 Spoken Dialogue Systems (SDS) Evaluation task. The main features supporting the UNITN SDS are the mixed initiative control, which allows the caller to get partly in control of the dialog strategy, and the descriptive specification of dialog strategies. The application is based on a complex,...
متن کاملThe EVALITA Dependency Parsing Task: From 2007 to 2011
The aim of the EVALITA Parsing Task (EPT) is at defining and extending Italian state-of-the-art parsing by encouraging the application of existing models and approaches, comparing paradigms and annotation formats. Therefore, in all the editions, held respectively in 2007, 2009 and 2011, the Task has been organized around two tracks, namely Dependency Parsing and Constituency Parsing, exploiting...
متن کاملThe Evalita 2011 Parsing Task: the Dependency Track
The aim of Evalita Parsing Task is at defining and extending Italian state of the art parsing by encouraging the application of existing models and approaches. As in the Evalita’07 and ’09, the Task is organized around two tracks, i.e. Dependency Parsing and Constituency Parsing. In this paper, we describe only the Dependency Parsing track by presenting the data sets for development and testing...
متن کاملComparing Italian parsers on a common Treebank: the EVALITA experience
The Evalita ’07 Parsing Task has been the first contest among parsing systems for Italian. It is the first attempt to compare the approaches and the results of the existing parsing systems specific for this language using a common treebank annotated using both a dependency and a constituency-based format. The development data set for this parsing competition was taken from the Turin University ...
متن کامل