Incremental, Predictive Parsing with Psycholinguistically motivatedTree-adjoining grammar
- 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.
Author details: | Vera Demberg, Frank Keller, Alexander Koller |
---|---|
DOI: | https://doi.org/10.1162/COLI_a_00160 |
ISSN: | 0891-2017 |
ISSN: | 1530-9312 |
Title of parent work (English): | Computational linguistics |
Publisher: | MIT Press |
Place of publishing: | Cambridge |
Publication type: | Article |
Language: | English |
Year of first publication: | 2013 |
Publication year: | 2013 |
Release date: | 2017/03/26 |
Volume: | 39 |
Issue: | 4 |
Number of pages: | 42 |
First page: | 1025 |
Last Page: | 1066 |
Funding institution: | EPSRC [EP/C546830/1] |
Organizational units: | Humanwissenschaftliche Fakultät / Strukturbereich Kognitionswissenschaften / Department Linguistik |
Peer review: | Referiert |
Publishing method: | Open Access |
Institution name at the time of the publication: | Humanwissenschaftliche Fakultät / Institut für Linguistik / Allgemeine Sprachwissenschaft |