Automatic extraction of subcategorization from corpora
ANLC '97 Proceedings of the fifth conference on Applied natural language processing
Automatic verb classification based on statistical distributions of argument structure
Computational Linguistics
Applied morphological processing of English
Natural Language Engineering
Using semantic preferences to identify verbal participation in role switching alternations
NAACL 2000 Proceedings of the 1st North American chapter of the Association for Computational Linguistics conference
Acquiring lexical generalizations from corpora: a case study for diathesis alternations
ACL '99 Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics
Learning verb argument structure from minimally annotated corpora
COLING '02 Proceedings of the 19th international conference on Computational linguistics - Volume 1
Crosslinguistic transfer in automatic verb classification
COLING '02 Proceedings of the 19th international conference on Computational linguistics - Volume 1
MEANING: a roadmap to knowledge technologies
COLING-Roadmap '02 Proceedings of the 2002 COLING workshop: A roadmap for computational linguistics - Volume 13
Automatic verb classification using multilingual resources
ConLL '01 Proceedings of the 2001 workshop on Computational Natural Language Learning - Volume 7
Unsupervised discovery of a statistical verb lexicon
EMNLP '06 Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing
Unsupervised induction of semantic roles
HLT '10 Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Hi-index | 0.00 |
We present a method for automatically identifying verbal participation in diathesis alternations. Automatically acquired subcategorization frames are compared to a hand-crafted classification for selecting candidate verbs. The minimum description length principle is then used to produce a model and cost for storing the head noun instances from a training corpus at the relevant argument slots. Alternating subcategorization frames are identified where the data from corresponding argument slots in the respective frames can be combined to produce a cheaper model than that produced if the data is encoded separately.