- Abstract:
-
We explore the use of restricted dialogue contexts in reinforcement learning (RL) of effective dialogue strategies for information seeking spoken dialogue systems (e.g. COMMUNICATOR). The contexts we use are richer than previous research in this area, which use only slot-based information, but are much less complex than the full dialogue ``Information States'' explored in Henderson et a. 2005, for which tractability is an issue. We explore how incrementally adding richer features allows learning of more effective dialogue strategies. We use 2 user simulations learned from COMMUNICATOR data to explore the effects of different features on learned dialogue strategies. Our results show that adding the last system and user dialogue moves
increases the average reward of the automatically learned strategies
by 65.9% over the original (hand-coded) COMMUNICATOR systems, and by 7.8% over a baseline RL policy that uses only slot-status features. We show that the new strategies exhibit a ``focus switching'' strategy and effective use of the `give help' action.
- Links To Paper
- Author homepage
- Project website
- Bibtex format
- @InProceedings{EDI-INF-RR-0899,
- author = {
Matthew Frampton
and Oliver Lemon
},
- title = {Learning More Effective Dialogue Strategies Using Limited Dialogue Move Features},
- book title = {Association for Computational Lingusitics},
- year = 2006,
- pages = {185-192},
- doi = {10.3115/1220175.1220199},
- url = {http://homepages.inf.ed.ac.uk/olemon/},
- }
|
