Title
Generation that exploits corpus-based statistical knowledge
Abstract
We describe novel aspects of a new natural language generator called Nitrogen. This generator has a highly flexible input representation that allows a spectrum of input from syntactic to semantic depth, and shifts the burden of many linguistic decisions to the statistical post-processor. The generation algorithm is compositional, making it efficient, yet it also handles non-compositional aspects of language. Nitrogen's design makes it robust and scalable, operating with lexicons and knowledge bases of one hundred thousand entities.
Year
DOI
Venue
1998
10.3115/980451.980963
meeting of the association for computational linguistics
Keywords
DocType
Volume
non-compositional aspect,statistical knowledge,hundred thousand entity,novel aspect,knowledge base,generation algorithm,flexible input representation,linguistic decision,statistical post-processor,new natural language generator
Conference
P98-1
Citations 
PageRank 
References 
182
18.68
5
Authors
2
Search Limit
100182
Name
Order
Citations
PageRank
Irene Langkilde135137.99
Kevin Knight25096462.44