%0 Conference Paper %1 Bergsma:EtAl:10 %A Bergsma, Shane %A Pitler, Emily %A Lin, Dekang %B Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics (ACL-10) %D 2010 %K 2010 acl bracketing compounds %T Creating Robust Supervised Classifiers via Web-Scale N-gram Data %U http://aclweb.org/anthology-new/P/P10/P10-1089.pdf %X In this paper, we systematically assess the value of using web-scale N-gram data in state-of-the-art supervised NLP classifiers. We compare classifiers that include or exclude features for the counts of various N-grams, where the counts are obtained from a web-scale auxiliary corpus. We show that including N-gram count features can advance the state-of-the-art accuracy on standard data sets for adjective ordering, spelling correction, noun compound bracketing, and verb part-of-speech disambiguation. More importantly, when operating on new domains, or when labeled training data is not plentiful, we show that using web-scale N-gram features is essential for achieving robust performance.

@inproceedings{Bergsma:EtAl:10, abstract = {In this paper, we systematically assess the value of using web-scale N-gram data in state-of-the-art supervised NLP classifiers. We compare classifiers that include or exclude features for the counts of various N-grams, where the counts are obtained from a web-scale auxiliary corpus. We show that including N-gram count features can advance the state-of-the-art accuracy on standard data sets for adjective ordering, spelling correction, noun compound bracketing, and verb part-of-speech disambiguation. More importantly, when operating on new domains, or when labeled training data is not plentiful, we show that using web-scale N-gram features is essential for achieving robust performance.}, added-at = {2011-04-05T03:33:20.000+0200}, author = {Bergsma, Shane and Pitler, Emily and Lin, Dekang}, biburl = {https://www.bibsonomy.org/bibtex/2728f8e1570f808f18ca0ac999c0d11f0/seandalai}, booktitle = {Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics (ACL-10)}, interhash = {37594315b68366fee1dac9d16d5467a4}, intrahash = {728f8e1570f808f18ca0ac999c0d11f0}, keywords = {2010 acl bracketing compounds}, timestamp = {2011-04-05T03:33:20.000+0200}, title = {Creating Robust Supervised Classifiers via Web-Scale N-gram Data}, url = {http://aclweb.org/anthology-new/P/P10/P10-1089.pdf}, year = 2010 }