Paper: Using Integer Linear Programming in Concept-to-Text Generation to Produce More Compact Texts

ACL ID P13-2100
Title Using Integer Linear Programming in Concept-to-Text Generation to Produce More Compact Texts
Venue Annual Meeting of the Association of Computational Linguistics
Session Short Paper
Year 2013
Authors

We present an ILP model of concept-to- text generation. Unlike pipeline archi- tectures, our model jointly considers the choices in content selection, lexicaliza- tion, and aggregation to avoid greedy de- cisions and produce more compact texts.