Statistical acquisition of content selection rules for natural language generation

Abstract

A Natural Language Generation system produces text using as input semantic data. One of its very first tasks is to decide which pieces of information to convey in the output. This task, called Content Selection, is quite domain dependent, requiring considerable re-engineering to transport the system from one scenario to another. In this paper, we present a method to acquire content selection rules automatically from a corpus of text and associated semantics. Our proposed technique was evaluated by comparing its output with information selected by human authors in unseen texts, where we were able to filter half the input data set without loss of recall.