An eye-tracking evaluation of some parser complexity metrics

Matthew James Green

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Information theoretic measures of incremental parser load were generated from a phrase structure parser and a dependency parser and then compared with incremental eye movement metrics collected for the same temporarily syntactically ambiguous sentences, focussing on the disambiguating word. The findings show that the surprisal and entropy reduction metrics computed over a phrase structure grammar make good candidates for predictors of text readability for human comprehenders. This leads to a suggestion for the use of such metrics in Natural Language Generation (NLG).
Original languageEnglish
Title of host publicationProceedings of The 3rd Workshop on Predicting and Improving Text Readability for Target Reader Populations
Place of PublicationStroudsburg, PA
PublisherACL Anthology
Pages38-46
Number of pages8
ISBN (Print)9781937284916
Publication statusPublished - 2014

    Fingerprint

Cite this

Green, M. J. (2014). An eye-tracking evaluation of some parser complexity metrics. In Proceedings of The 3rd Workshop on Predicting and Improving Text Readability for Target Reader Populations (pp. 38-46). ACL Anthology. http://www.aclweb.org/anthology/W14-1205