Welcome to the website of the Statistical Models of Grammaticality (SMOG) project in the Department of Philosophy at King's College London.
SMOG is exploring the construction of an enriched stochastic model that represents the syntactic knowledge that native speakers of English have of their language.
We are experimenting with different sorts of language models that contain a variety of parameters encoding properties of sentences and probability distributions over corpora.
You can get a clearer idea of our research by reading the papers in the section of the website.
You can also download our software and run our experiments on your own corpora, modifying parameters and changing the design of the model as you think appropriate.