Incremental, Predictive Parsing with Psycholinguistically Motivated Tree-Adjoining Grammar
Authors:
Open Access
- 1 December 2013
- journal article
- Published by MIT Press in Computational Linguistics
- Vol. 39 (4) , 1025-1066
Abstract
Psycholinguistic research shows that key properties of the human sentence processor are incrementality, connectedness (partial structures contain no unattached nodes), and prediction (upcoming syntactic structure is anticipated). There is currently no broad-coverage parsing model with these properties, however. In this article, we present the first broad-coverage probabilistic parser for PLTAG, a variant of TAG that supports all three requirements. We train our parser on a TAG-transformed version of the Penn Treebank and show that it achieves performance comparable to existing TAG parsers that are incremental but not predictive. We also use our PLTAG model to predict human reading times, demonstrating a better fit on the Dundee eye-tracking corpus than a standard surprisal model.Keywords
This publication has 40 references indexed in Scilit:
- The use of verb-specific information for prediction in sentence processingLanguage and Cognitive Processes, 2013
- Random effects structure for confirmatory hypothesis testing: Keep it maximalJournal of Memory and Language, 2013
- Incremental Processing of Coreference and Binding in JapaneseSyntax, 2009
- Data from eye-tracking corpora as evidence for theories of syntactic processing complexityCognition, 2008
- Incremental parsing with the perceptron algorithm2004
- Head-Driven Statistical Models for Natural Language ParsingComputational Linguistics, 2003
- Statistical parsing with an automatically-extracted tree adjoining grammar2000
- TnT2000
- Incremental interpretation at verbs: restricting the domain of subsequent referenceCognition, 1999
- Linguistic complexity: locality of syntactic dependenciesCognition, 1998