Information Extraction with HMM Structures Learned by Stochastic Optimization
Proceedings of the Seventeenth National Conference on Artificial Intelligence and Twelfth Conference on Innovative Applications of Artificial Intelligence
Learning accurate, compact, and interpretable tree annotation
ACL-44 Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the Association for Computational Linguistics
An Incrementally Trainable Statistical Approach to Information Extraction: Based on Token Classification and Rich Context Model
A unified model of phrasal and sentential evidence for information extraction
EMNLP '09 Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 1 - Volume 1
Coreference resolution in a modular, entity-centered model
HLT '10 Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Generality and reuse in a common type system for clinical natural language processing
Proceedings of the first international workshop on Managing interoperability and complexity in health systems
Structured databases of named entities from Bayesian nonparametrics
EMNLP '11 Proceedings of the First Workshop on Unsupervised Learning in NLP
A probabilistic model for canonicalizing named entity mentions
ACL '12 Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers - Volume 1
Discriminative learning for joint template filling
ACL '12 Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers - Volume 1
| Hi-index | 0.00 |
We present a generative model of template-filling in which coreference resolution and role assignment are jointly determined. Underlying template roles first generate abstract entities, which in turn generate concrete textual mentions. On the standard corporate acquisitions dataset, joint resolution in our entity-level model reduces error over a mention-level discriminative approach by up to 20%.