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

ACL ID P11-2115
Title Hierarchical Reinforcement Learning and Hidden Markov Models for Task-Oriented Natural Language Generation
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2011
Authors

Surface realisation decisions in language gen- eration 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 func- tion 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.