Parameter Estimation for LDA-Frames
LDA-frames is an unsupervised approach for identifying semantic frames from
semantically unlabeled text corpora, and seems
to be a useful competitor for manually created databases of selectional
The most limiting property of the algorithm is such that the number of frames
and roles must be predefined.
In this paper we present a modification of the LDA-frames algorithm allowing
the number of frames and roles to be determined automatically, based on the
character and size of training data.
Back to Papers Accepted