Experiments with an Annotation Scheme for a Knowledge-rich Noun Phrase Interpretation System
R. Girju. Proceedings of the ACL Linguistic Annotation Workshop, page 168--175. Prague, Czech Republic, Association for Computational Linguistics, (June 2007)
Abstract
This paper presents observations on our experience with an annotation scheme that was used in the training of a state-of-the-art noun phrase semantic interpretation system. The system relies on cross-linguistic evidence from a set of five Romance languages: Spanish, Italian, French, Portuguese, and Romanian. Given a training set of English noun phrases in context along with their translations in the five Romance languages, our algorithm automatically learns a classification function that is later on applied to unseen test instances for semantic interpretation. As training and test data we used two text collections of different genre: Europarl and CLUVI. The training data was annotated with contextual features based on two state-of-the-art classification tag sets.
%0 Conference Paper
%1 Girju:07a
%A Girju, Roxana
%B Proceedings of the ACL Linguistic Annotation Workshop
%C Prague, Czech Republic
%D 2007
%I Association for Computational Linguistics
%K 2007 annotation compounds workshop
%P 168--175
%T Experiments with an Annotation Scheme for a Knowledge-rich Noun Phrase Interpretation System
%U http://acl.ldc.upenn.edu/W/W07/W07-1527.pdf
%X This paper presents observations on our experience with an annotation scheme that was used in the training of a state-of-the-art noun phrase semantic interpretation system. The system relies on cross-linguistic evidence from a set of five Romance languages: Spanish, Italian, French, Portuguese, and Romanian. Given a training set of English noun phrases in context along with their translations in the five Romance languages, our algorithm automatically learns a classification function that is later on applied to unseen test instances for semantic interpretation. As training and test data we used two text collections of different genre: Europarl and CLUVI. The training data was annotated with contextual features based on two state-of-the-art classification tag sets.
@inproceedings{Girju:07a,
abstract = {This paper presents observations on our experience with an annotation scheme that was used in the training of a state-of-the-art noun phrase semantic interpretation system. The system relies on cross-linguistic evidence from a set of five Romance languages: Spanish, Italian, French, Portuguese, and Romanian. Given a training set of English noun phrases in context along with their translations in the five Romance languages, our algorithm automatically learns a classification function that is later on applied to unseen test instances for semantic interpretation. As training and test data we used two text collections of different genre: Europarl and CLUVI. The training data was annotated with contextual features based on two state-of-the-art classification tag sets.},
added-at = {2007-07-09T17:56:34.000+0200},
address = {Prague, Czech Republic},
author = {Girju, Roxana},
biburl = {https://www.bibsonomy.org/bibtex/24f6c1bba174660bb81ca07aced6e0f0d/seandalai},
booktitle = {Proceedings of the ACL Linguistic Annotation Workshop},
interhash = {e0569b5c0f7238d2de6dfad0a5c324d7},
intrahash = {4f6c1bba174660bb81ca07aced6e0f0d},
keywords = {2007 annotation compounds workshop},
month = {June},
pages = {168--175},
publisher = {Association for Computational Linguistics},
timestamp = {2007-07-09T17:56:34.000+0200},
title = {Experiments with an Annotation Scheme for a Knowledge-rich Noun Phrase Interpretation System},
url = {http://acl.ldc.upenn.edu/W/W07/W07-1527.pdf},
year = 2007
}