Towards a Statistical Model of Grammaticality

Research output: Chapter in Book/Report/Conference proceedingPoster abstractpeer-review

7 Citations (Scopus)


The question of whether it is possible to characterise grammatical
knowledge in probabilistic terms is central to determining
the relationship of linguistic representation to other cognitive
domains. We present a statistical model of grammaticality
which maps the probabilities of a statistical model for
sentences in parts of the British National Corpus (BNC) into
grammaticality scores, using various functions of the parameters
of the model. We test this approach with a classifier on test
sets containing different levels of syntactic infelicity. With appropriate
tuning, the classifiers achieve encouraging levels of
accuracy. These experiments suggest that it may be possible to
characterise grammaticality judgements in probabilistic terms
using an enriched language model.
Original languageEnglish
Title of host publicationProceedings of the 35th Annual Conference of the Cognitive Science Society 2013
Place of PublicationBerlin
PublisherCognitive Science Society.
Number of pages6
ISBN (Print)978-0-9768318-9-1
Publication statusPublished - 31 Jul 2013

Publication series

NameProceeding of the Annual Conference of the Cognitive Science Society


  • language models, grammaticality, statistical model of grammaticality


Dive into the research topics of 'Towards a Statistical Model of Grammaticality'. Together they form a unique fingerprint.

Cite this