http://cogprints.org/4204/
On Parsing CHILDES
Research on child language acquisition would benefit from the availability of a large body of syntactically parsed utterances between parents and children. We consider the problem of generating such a ``treebank'' from the CHILDES corpus, which currently contains primarily orthographically transcribed speech tagged for lexical category.
Laakso, Aarre
Computational Linguistics
Aarre
Laakso