Title |
Comparing the Influence of Different Treebank Annotations on Dependency Parsing |
Authors |
Cristina Bosco, Simonetta Montemagni, Alessandro Mazzei, Vincenzo Lombardo, Felice Dell'Orletta, Alessandro Lenci, Leonardo Lesmo, Giuseppe Attardi, Maria Simi, Alberto Lavelli, Johan Hall, Jens Nilsson and Joakim Nivre |
Abstract |
As the interest of the NLP community grows to develop several treebanks also for languages other than English, we observe efforts towards evaluating the impact of different annotation strategies used to represent particular languages or with reference to particular tasks. This paper contributes to the debate on the influence of resources used for the training and development on the performance of parsing systems. It presents a comparative analysis of the results achieved by three different dependency parsers developed and tested with respect to two treebanks for the Italian language, namely TUT and ISST--TANL, which differ significantly at the level of both corpus composition and adopted dependency representations. |
Topics |
Parsing, Corpus (creation, annotation, etc.), Evaluation methodologies |
Full paper |
Comparing the Influence of Different Treebank Annotations on Dependency Parsing |
Slides |
- |
Bibtex |
@InProceedings{BOSCO10.196,
author = {Cristina Bosco and Simonetta Montemagni and Alessandro Mazzei and Vincenzo Lombardo and Felice Dell'Orletta and Alessandro Lenci and Leonardo Lesmo and Giuseppe Attardi and Maria Simi and Alberto Lavelli and Johan Hall and Jens Nilsson and Joakim Nivre}, title = {Comparing the Influence of Different Treebank Annotations on Dependency Parsing}, booktitle = {Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10)}, year = {2010}, month = {may}, date = {19-21}, address = {Valletta, Malta}, editor = {Nicoletta Calzolari (Conference Chair) and Khalid Choukri and Bente Maegaard and Joseph Mariani and Jan Odijk and Stelios Piperidis and Mike Rosner and Daniel Tapias}, publisher = {European Language Resources Association (ELRA)}, isbn = {2-9517408-6-7}, language = {english} } |