6 March: DCLRS Mar 8, J Wagner (DCU), Grammatical errors

Dublin Computational Linguistics Research Seminar: Index of March 2013 | Dublin Computational Linguistics Research Seminar - Index of year: 2013 | Full index

Science),
Dr Joachim Wagner (DCU) speaks on

Detecting grammatical errors using probabilistic parsing with
treebank-induced grammars

Today's dominant parsing technology uses grammars that have been
automatically induced from treebanks, i.e. text annotated with syntactic
structures. Given sufficiently large treebanks, such grammars tend to be
highly robust to unexpected input and achieve wide coverage of
unrestricted text. These are desirable properties in many applications.
However, the robustness also covers grammatical errors. Almost all input
is parsed into a (more or less plausible) parse tree, meaning that
parsability cannot be used as a criterion for grammaticality. In this
talk, I present three methods for applying probabilistic, treebank-
induced grammars to the task of automatically judging the grammaticality
of an input string. The best-performing method exploits the differences
between parse results for grammars trained on grammatical and
ungrammatical treebanks. This method combines well with n-gram and deep
grammar-based approaches, as well as combinations thereof, in a machine
learning-based framework. To address uncertain miss-classification costs
and varying error densities, methods are evaluated with accuracy curves
(which are related to ROC curves) and, during training, a set of optimal
classifiers is selected from the ROC convex hull.

www.scss.tcd.ie/disciplines/intelligent_systems/clg/clg_web/DCLRS

_______________________________________________
cogsci mailing list
cogsci@scss.tcd.ie
https://lists.scss.tcd.ie/mailman/listinfo/cogsci

Dublin Computational Linguistics Research Seminar - Index of March 2013 | Index of year: 2013 | Full index