Presentations (Communicative Events)

Content planner construction via evolutionary algorithms and a corpus-based fitness function

McKeown, Kathleen; Duboue, Pablo A.

In this paper, we present a novel technique to learn a tree-like structure for a content planner from an aligned corpus of semantic inputs and corresponding, human-produced, outputs. We apply a stochastic search mechanism with a two-level fitness function. As a first stage, we use high level order constraints to quickly discard unpromising planners. As a second stage, alignments between regenerated text and human output are employed. We evaluate our approach by using the existing symbolic planner in our system as a gold standard, obtaining a 66 % improvement over a random baseline in just 20 generations of genetic search.


More About This Work

Academic Units
Computer Science
Proceedings of the Second International Natural Language Generation Conference (INLG 2002)
Published Here
May 10, 2013