Calibrating features for semantic role labeling. Xue, N. & Palmer, M. In Proceedings of EMNLP, volume 4, pages 88-94, 2004. In Proceedings of EMNLP 2004.
abstract   bibtex   
This paper takes a critical look at the features used in the semantic role tagging literature and show that the information in the input, generally a syntactic parse tree, has yet to be fully exploited. We propose an additional set of features and our experiments show that these features lead to fairly significant improvements in the tasks we performed. We further show that different features are needed for different subtasks. Finally, we show that by using a Maximum Entropy classifier and fewer features, we achieved results comparable with the best previously reported results obtained with SVM models. We believe this is a clear indication that developing features that capture the right kind of information is crucial to advancing the stateof-the-art in semantic analysis. 1
@inProceedings{
 title = {Calibrating features for semantic role labeling},
 type = {inProceedings},
 year = {2004},
 pages = {88-94},
 volume = {4},
 publisher = {In Proceedings of EMNLP 2004},
 editors = {[object Object],[object Object]},
 id = {1b26be28-afb7-3ac8-9668-ad9ee00a765c},
 created = {2012-04-01T16:32:49.000Z},
 file_attached = {false},
 profile_id = {5284e6aa-156c-3ce5-bc0e-b80cf09f3ef6},
 group_id = {066b42c8-f712-3fc3-abb2-225c158d2704},
 last_modified = {2017-03-14T14:36:19.698Z},
 tags = {semantic role labeling},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {Xue2004},
 private_publication = {false},
 abstract = {This paper takes a critical look at the features used in the semantic role tagging literature and show that the information in the input, generally a syntactic parse tree, has yet to be fully exploited. We propose an additional set of features and our experiments show that these features lead to fairly significant improvements in the tasks we performed. We further show that different features are needed for different subtasks. Finally, we show that by using a Maximum Entropy classifier and fewer features, we achieved results comparable with the best previously reported results obtained with SVM models. We believe this is a clear indication that developing features that capture the right kind of information is crucial to advancing the stateof-the-art in semantic analysis. 1},
 bibtype = {inProceedings},
 author = {Xue, Nianwen and Palmer, Martha},
 booktitle = {Proceedings of EMNLP}
}

Downloads: 0