Paper: On the Feasibility of Automatically Describing n-dimensional Objects

ACL ID W13-2123
Title On the Feasibility of Automatically Describing n-dimensional Objects
Venue European Workshop on Natural Language Generation
Session
Year 2013
Authors

This paper introduces the problem of gen- erating descriptions of n-dimensional spa- tial data by decomposing it via model- based clustering. I apply the approach to the error function of supervised clas- sification algorithms, a practical problem that uses Natural Language Generation for understanding the behaviour of a trained classifier. I demonstrate my system on a dataset taken from CoNLL shared tasks.