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. |
Year | Venue | Keywords |
---|---|---|
2010 | language resources and evaluation | dependency parsing,computational linguistics,comparative analysis |
Field | DocType | Citations |
Training and development,Annotation,Computer science,Computational linguistics,Dependency grammar,Treebank,Natural language processing,Artificial intelligence,Parsing | Conference | 9 |
PageRank | References | Authors |
0.74 | 5 | 13 |
Name | Order | Citations | PageRank |
---|---|---|---|
Cristina Bosco | 1 | 200 | 28.56 |
Simonetta Montemagni | 2 | 255 | 33.40 |
Simonetta Montemagni | 3 | 255 | 33.40 |
Vincenzo Lombardo | 4 | 358 | 53.15 |
Felice Dell'Orletta | 5 | 207 | 34.46 |
Felice Dell'Orletta | 6 | 207 | 34.46 |
Alessandro Lenci | 7 | 633 | 61.92 |
Giuseppe Attardi | 8 | 545 | 101.27 |
Giuseppe Attardi | 9 | 545 | 101.27 |
Alberto Lavelli | 10 | 615 | 55.37 |
Alberto Lavelli | 11 | 615 | 55.37 |
Jens Nilsson | 12 | 556 | 39.88 |
Joakim Nivre | 13 | 3652 | 229.07 |