An efficient probabilistic context-free parsing algorithm that computes prefix probabilities
Computational Linguistics
A machine learning approach to coreference resolution of noun phrases
Computational Linguistics - Special issue on computational anaphora resolution
Probabilistic parsing and psychological plausibility
COLING '00 Proceedings of the 18th conference on Computational linguistics - Volume 1
A probabilistic earley parser as a psycholinguistic model
NAACL '01 Proceedings of the second meeting of the North American Chapter of the Association for Computational Linguistics on Language technologies
Machine Learning
Using the web in machine learning for other-anaphora resolution
EMNLP '03 Proceedings of the 2003 conference on Empirical methods in natural language processing
Surprising parser actions and reading difficulty
HLT-Short '08 Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics on Human Language Technologies: Short Papers
Joint unsupervised coreference resolution with Markov logic
EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Syntactic and semantic factors in processing difficulty: an integrated measure
ACL '10 Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics
Cognitively plausible models of human language processing
ACLShort '10 Proceedings of the ACL 2010 Conference Short Papers
A model of discourse predictions in human sentence processing
EMNLP '11 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Hi-index | 0.00 |
Probabilistic models of sentence comprehension are increasingly relevant to questions concerning human language processing. However, such models are often limited to syntactic factors. This paper introduces a novel sentence processing model that consists of a parser augmented with a probabilistic logic-based model of coreference resolution, which allows us to simulate how context interacts with syntax in a reading task. Our simulations show that a Weakly Interactive cognitive architecture can explain data which had been provided as evidence for the Strongly Interactive hypothesis.