Distributed Representations, Simple Recurrent Networks, And Grammatical Structure
Machine Learning - Connectionist approaches to language learning
An efficient probabilistic context-free parsing algorithm that computes prefix probabilities
Computational Linguistics
Probabilistic top-down parsing and language modeling
Computational Linguistics
PCFG models of linguistic tree representations
Computational Linguistics
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
Accurate unlexicalized parsing
ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
The Penn Treebank: annotating predicate argument structure
HLT '94 Proceedings of the workshop on Human Language Technology
EMNLP '09 Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 1 - Volume 1
AAAI'96 Proceedings of the thirteenth national conference on Artificial intelligence - Volume 2
Incremental, predictive parsing with psycholinguistically motivated tree-adjoining grammar
Computational Linguistics
| Hi-index | 0.00 |
Experimental evidence demonstrates that syntactic structure influences human online sentence processing behavior. Despite this evidence, open questions remain: which type of syntactic structure best explains observed behavior--hierarchical or sequential, and lexicalized or unlexicalized? Recently, Frank and Bod (2011) find that unlexicalized sequential models predict reading times better than unlexicalized hierarchical models, relative to a baseline prediction model that takes word-level factors into account. They conclude that the human parser is insensitive to hierarchical syntactic structure. We investigate these claims and find a picture more complicated than the one they present. First, we show that incorporating additional lexical n-gram probabilities estimated from several different corpora into the baseline model of Frank and Bod (2011) eliminates all differences in accuracy between those unlexicalized sequential and hierarchical models. Second, we show that lexicalizing the hierarchical models used in Frank and Bod (2011) significantly improves prediction accuracy relative to the unlexicalized versions. Third, we show that using state-of-the-art lexicalized hierarchical models further improves prediction accuracy. Our results demonstrate that the claim of Frank and Bod (2011) that sequential models predict reading times better than hierarchical models is premature, and also that lexicalization matters for prediction accuracy.