A maximum entropy approach to natural language processing
Computational Linguistics
Building a large annotated corpus of English: the penn treebank
Computational Linguistics - Special issue on using large corpora: II
Evaluating sense disambiguation across diverse parameter spaces
Natural Language Engineering
COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 1
Preposition semantic classification via Penn Treebank and FrameNet
CONLL '03 Proceedings of the seventh conference on Natural language learning at HLT-NAACL 2003 - Volume 4
Exploiting semantic role resources for preposition disambiguation
Computational Linguistics
11,001 new features for statistical machine translation
NAACL '09 Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Disambiguation of preposition sense using linguistically motivated features
SRWS '09 Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Companion Volume: Student Research Workshop and Doctoral Consortium
SemEval-2007 task 06: word-sense disambiguation of prepositions
SemEval '07 Proceedings of the 4th International Workshop on Semantic Evaluations
MELB-YB: preposition sense disambiguation using rich semantic features
SemEval '07 Proceedings of the 4th International Workshop on Semantic Evaluations
Towards a domain independent semantics: enhancing semantic representation with construction grammar
EUCCL '10 Proceedings of the NAACL HLT Workshop on Extracting and Using Constructions in Computational Linguistics
Models and training for unsupervised preposition sense disambiguation
HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies: short papers - Volume 2
A joint model for extended semantic role labeling
EMNLP '11 Proceedings of the Conference on Empirical Methods in Natural Language Processing
A fast, accurate, non-projective, semantically-enriched parser
EMNLP '11 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Exploiting partial annotations with EM training
WILS '12 Proceedings of the NAACL-HLT Workshop on the Induction of Linguistic Structure
| Hi-index | 0.00 |
Choosing the right parameters for a word sense disambiguation task is critical to the success of the experiments. We explore this idea for prepositions, an often overlooked word class. We examine the parameters that must be considered in preposition disambiguation, namely context, features, and granularity. Doing so delivers an increased performance that significantly improves over two state-of-the-art systems, and shows potential for improving other word sense disambiguation tasks. We report accuracies of 91.8% and 84.8% for coarse and fine-grained preposition sense disambiguation, respectively.