Publishing Partner: Cambridge University Press CUP Extra Publisher Login
amazon logo
More Info


New from Oxford University Press!

ad

How Traditions Live and Die

By Olivier Morin

This book brings together cognitive science and quantitative cultural history to look into the causes of cultural survival.


New from Cambridge University Press!

ad

The Acquisition of Heritage Languages

By Silvina Montrul

"This work centres on the grammatical development of the heritage language and the language learning trajectory of heritage speakers, synthesizing recent experimental research."


Academic Paper


Title: Does this list contain what you were searching for? Learning adaptive dialogue strategies for interactive question answering
Author: Verena Rieser
Email: click here TO access email
Homepage: http://homepages.inf.ed.ac.uk/vrieser/
Institution: University of Edinburgh
Author: Oliver Lemon
Institution: University of Edinburgh
Linguistic Field: Applied Linguistics
Abstract: Policy learning is an active topic in dialogue systems research, but it has not been explored in relation to interactive question answering (IQA). We take a first step in learning adaptive interaction policies for question answering : we address the question of how to acquire enough reliable query constraints, how many database results to present to the user and when to present them, given the competing trade-offs between the length of the answer list, the length of the interaction, the type of database and the noise in the communication channel. The operating conditions are reflected in an objective function which we use to derive a hand-coded threshold-based policy and rewards to train a reinforcement learning policy. The same objective function is used for evaluation. We show that we can learn strategies for this complex trade-off problem which perform significantly better than a variety of hand-coded policies, for a wide range of noise conditions, user types, types of DB and turn-penalties. Our policy learning framework thus covers a wide spectrum of operating conditions. The learned policies produce an average increase in reward of 86.78% over the hand-coded policies. In 93% of the cases the learned policies perform significantly better than the hand-coded ones ( < .001). Furthermore we show that the type of database has a significant effect on learning and we give qualitative descriptions of the learned IQA policies.

CUP AT LINGUIST

This article appears IN Natural Language Engineering Vol. 15, Issue 1, which you can READ on Cambridge's site or on LINGUIST .



Add a new paper
Return to Academic Papers main page
Return to Directory of Linguists main page