Abstract

Natural language generation (NLG) is the task of generating natural language from a meaning representation. Rule-based approaches require domain-specific and manually constructed linguistic resources, while most corpus based approaches rely on aligned training data and/or phrase templates. The latter are needed to restrict the search space for the structured prediction task defined by the unaligned datasets.

In this talk we will discuss the use of imitation learning for structured prediction which learns an incremental model that handles the large search space while avoiding explicitly enumerating it. We will show how we adapted the Locally Optimal Learning to Search (Chang et al., 2015) framework which allows us to train against non-decomposable loss functions such as the BLEU or ROUGE scores while not assuming gold standard alignments. We will show the results of our evaluation on three datasets using both automatic measures and human judgements which achieves results comparable to the state-of-the-art approaches developed for each of them. Furthermore, we will present an analysis of the datasets which examines common issues with NLG evaluation.