| Y. Krymolowski and D Roth. Incorporating knowledge in natural language learning: A case study. In Workshop on the usage of WordNet in Natural Language Processing Systems, Montreal, Canada, aug 1998. http://l2r.cs.uiuc.edu/ danr. |
....Introduction WordNet [ Miller et al. 1991 ] is an ontology widely used by the natural language processing (NLP) community. The information contained in WordNet can be used in a lot of reasoning tasks to solve a set of NL problems (Part of speech tagging [ Segond et al. 1997 ] PP attachment [ Krymolowski and Roth, 1998 ] WSD [ Resnik, 1997, Sussna, 1993, Voorhees, 1993, Wiebe et al. 1998 ] information extraction [ Chai and Biermann, 1997 ] Nevertheless, no reasoning procedure is provided by WordNet itself. It only provides information. Mainly it provides ontological information about concepts ....
Y. Krymolowski and D Roth. Incorporating knowledge in natural language learning: A case study. In Workshop on the usage of WordNet in Natural Language Processing Systems, Montreal, Canada, aug 1998. http://l2r.cs.uiuc.edu/ danr.
....are the common features used anyhow by most learning algorithms applied to various disambiguation and predictions tasks in NLP. For example, various methods have been used to study the PPA problem discussed in Ex. 3. 1 [ Collins and Brooks, 1995; Brill and Resnik, 1994; Ratnaparkhi et al. 1994; Krymolowski and Roth, 1998 ] All of them make use of essentially the same conjunctive features presented here. The same holds for many other problems. We conclude that MBL methods are linear over feature spaces that are commonly used for learning in NLP. Space Considerations The bound on the total number of features ....
Y. Krymolowski and D. Roth. Incorporating knowledge in natural language learning: A case study. In COLING-ACL'98 workshop on the Usage of WordNet in Natural Language Processing Systems, 1998.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC