The syntactic process
Supertagging: an approach to almost parsing
Computational Linguistics
Efficient normal-form parsing for combinatory categorial grammar
ACL '96 Proceedings of the 34th annual meeting on Association for Computational Linguistics
Unsupervised learning of field segmentation models for information extraction
ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
Part of speech tagging in context
COLING '04 Proceedings of the 20th international conference on Computational Linguistics
Prototype-driven learning for sequence models
HLT-NAACL '06 Proceedings of the main conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics
CCGbank: A Corpus of CCG Derivations and Dependency Structures Extracted from the Penn Treebank
Computational Linguistics
Wide-coverage efficient statistical parsing with ccg and log-linear models
Computational Linguistics
Multilingual deep lexical acquisition for HPSGs via supertagging
EMNLP '06 Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing
CCG supertags in factored statistical machine translation
StatMT '07 Proceedings of the Second Workshop on Statistical Machine Translation
Minimized models and grammar-informed initialization for supertagging with highly ambiguous lexicons
ACL '10 Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics
Hi-index | 0.00 |
Much previous work has investigated weak supervision with HMMs and tag dictionaries for part-of-speech tagging, but there have been no similar investigations for the harder problem of supertagging. Here, I show that weak supervision for supertagging does work, but that it is subject to severe performance degradation when the tag dictionary is highly ambiguous. I show that lexical category complexity and information about how supertags may combine syntactically can be used to initialize the transition distributions of a first-order Hidden Markov Model for weakly supervised learning. This initialization proves more effective than starting with uniform transitions, especially when the tag dictionary is highly ambiguous.