LOR-KBGEN, A Hybrid Approach To Generating from the KBGen Knowledge-Base
Bikash Gyawali, Claire Gardent · 2013
This abstract describes a contribution to the 2013 KBGen Challenge from CNRS/LORIA and the University of Lorraine. Our contribution focuses on an attempt to automate the extraction of a Feature Based Tree Adjoining Grammar equipped with a unification based compositional semantics which can be used to generate from KBGen data. Introduction Semantic grammars, i.e., grammars which link syntax and semantics, have been shown to be useful for generation and for semantic parsing. This abstract outlines an attempt to