A general feature space for automatic verb classification. Joanis, E. & Stevenson, S. In Proceedings of the 11th Conference of the European Chapter of the Association for Computational Linguistics (EACL-03), Budapest, Hungary, April, 2003. abstract bibtex We develop a general feature space for automatic classification of verbs into lexical semantic classes. Previous work was limited in scope by the need for manual selection of discriminating features, through a linguistic analysis of the target verb classes (Merlo and Stevenson, 2001). We instead analyze the classification structure at a higher level, using the possible defining characteristics of classes as the basis for our feature space. The general feature space achieves reductions in error rates of 42–69%, on a wider range of classes than investigated previously, with comparable performance to feature sets manually selected for the particular classification tasks. Our results show that the approach is generally applicable, and avoids the need for resource-intensive linguistic analysis for each new task.
@InProceedings{ joanis2,
author = {Eric Joanis and Suzanne Stevenson},
title = {A general feature space for automatic verb classification},
booktitle = {Proceedings of the 11th Conference of the European Chapter
of the Association for Computational Linguistics (EACL-03)},
address = {Budapest, Hungary},
month = {April},
year = {2003},
abstract = {We develop a general feature space for automatic
classification of verbs into lexical semantic classes.
Previous work was limited in scope by the need for manual
selection of discriminating features, through a linguistic
analysis of the target verb classes (Merlo and Stevenson,
2001). We instead analyze the classification structure at a
higher level, using the possible defining characteristics
of classes as the basis for our feature space. The general
feature space achieves reductions in error rates of
42--69\%, on a wider range of classes than investigated
previously, with comparable performance to feature sets
manually selected for the particular classification tasks.
Our results show that the approach is generally applicable,
and avoids the need for resource-intensive linguistic
analysis for each new task.},
download = {http://www.cs.toronto.edu/~joanis/Papers/eacl03-camera.pdf}
}
Downloads: 0
{"_id":{"_str":"534282740e946d920a001b9a"},"__v":8,"authorIDs":["5457f20a2abc8e9f370008f4","54643dbb4f4818cf4f00057d"],"author_short":["Joanis, E.","Stevenson, S."],"bibbaseid":"joanis-stevenson-ageneralfeaturespaceforautomaticverbclassification-2003","bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["Eric"],"propositions":[],"lastnames":["Joanis"],"suffixes":[]},{"firstnames":["Suzanne"],"propositions":[],"lastnames":["Stevenson"],"suffixes":[]}],"title":"A general feature space for automatic verb classification","booktitle":"Proceedings of the 11th Conference of the European Chapter of the Association for Computational Linguistics (EACL-03)","address":"Budapest, Hungary","month":"April","year":"2003","abstract":"We develop a general feature space for automatic classification of verbs into lexical semantic classes. Previous work was limited in scope by the need for manual selection of discriminating features, through a linguistic analysis of the target verb classes (Merlo and Stevenson, 2001). We instead analyze the classification structure at a higher level, using the possible defining characteristics of classes as the basis for our feature space. The general feature space achieves reductions in error rates of 42–69%, on a wider range of classes than investigated previously, with comparable performance to feature sets manually selected for the particular classification tasks. Our results show that the approach is generally applicable, and avoids the need for resource-intensive linguistic analysis for each new task.","download":"http://www.cs.toronto.edu/~joanis/Papers/eacl03-camera.pdf","bibtex":"@InProceedings{\t joanis2,\n author\t= {Eric Joanis and Suzanne Stevenson},\n title\t\t= {A general feature space for automatic verb classification},\n booktitle\t= {Proceedings of the 11th Conference of the European Chapter\n\t\t of the Association for Computational Linguistics (EACL-03)},\n address\t= {Budapest, Hungary},\n month\t\t= {April},\n year\t\t= {2003},\n abstract\t= {We develop a general feature space for automatic\n\t\t classification of verbs into lexical semantic classes.\n\t\t Previous work was limited in scope by the need for manual\n\t\t selection of discriminating features, through a linguistic\n\t\t analysis of the target verb classes (Merlo and Stevenson,\n\t\t 2001). We instead analyze the classification structure at a\n\t\t higher level, using the possible defining characteristics\n\t\t of classes as the basis for our feature space. The general\n\t\t feature space achieves reductions in error rates of\n\t\t 42--69\\%, on a wider range of classes than investigated\n\t\t previously, with comparable performance to feature sets\n\t\t manually selected for the particular classification tasks.\n\t\t Our results show that the approach is generally applicable,\n\t\t and avoids the need for resource-intensive linguistic\n\t\t analysis for each new task.},\n download\t= {http://www.cs.toronto.edu/~joanis/Papers/eacl03-camera.pdf}\n\t\t \n}\n\n","author_short":["Joanis, E.","Stevenson, S."],"key":"joanis2","id":"joanis2","bibbaseid":"joanis-stevenson-ageneralfeaturespaceforautomaticverbclassification-2003","role":"author","urls":{},"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"www.cs.toronto.edu/~fritz/tmp/compling.bib","downloads":0,"keywords":[],"search_terms":["general","feature","space","automatic","verb","classification","joanis","stevenson"],"title":"A general feature space for automatic verb classification","year":2003,"dataSources":["n8jB5BJxaeSmH6mtR","6b6A9kbkw4CsEGnRX"]}