Publikation

Hierarchical Reinforcement Learning and Hidden Markov Models for Task-Oriented Natural Language Generation

Nina Dethlefs, Dr. Heriberto Cuayáhuitl

In: Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (ACL-HLT). Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (ACL-HLT-2011) 49th June 19-24 Portland Oregon United States Seiten 654-659 ISBN 978-1-932432-88-6 ACL 7/2011.

Abstrakt

Surface realisation decisions in language generation can be sensitive to a language model, but also to decisions of content selection. We therefore propose the joint optimisation of content selection and surface realisation using Hierarchical Reinforcement Learning (HRL). To this end, we suggest a novel reward function that is induced from human data and is especially suited for surface realisation. It is based on a generation space in the form of a Hidden Markov Model (HMM). Results in terms of task success and human-likeness sug- gest that our unified approach performs better than greedy or random baselines.

Projekte

hc-acl-hlt2011.pdf (pdf, 377 KB )

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence