Author :
Suendermann, D. ; Liscombe, J. ; Pieraccini, R.
Author_Institution :
SpeechCycle Labs., NY, USA
Abstract :
Contender (or what the academic community would refer to as a light version of reinforcement learning) is a simple technique to experiment with a number of competing paths in a (commercial) spoken dialog system. By randomly routing certain portions of traffic to individual paths and computing average rewards for each of the routes, the goal is to find out which one performs best. This paper is to do away with common uncertainties on how to set up contender weights, how much data needs to be accumulated to draw reliable conclusions, and how this all relates to the notion of statistical significance.
Keywords :
interactive systems; learning (artificial intelligence); statistical analysis; contender; reinforcement learning; spoken dialog system; Contender; commercial spoken dialog systems; statistical significance;
Conference_Titel :
Spoken Language Technology Workshop (SLT), 2010 IEEE
Conference_Location :
Berkeley, CA
Print_ISBN :
978-1-4244-7904-7
Electronic_ISBN :
978-1-4244-7902-3
DOI :
10.1109/SLT.2010.5700873
