End-to-end LSTM-based dialog control optimized with supervised and reinforcement learning Jason D. Williams and Geoffrey Zweig Microsoft Research One Microsoft Way, Redmond, WA 98052, USA {jason.williams,gzweig}@microsof

First Page		Document Content
Date: 2016-06-06 20:40:38		End-to-end LSTM-based dialog control optimized with supervised and reinforcement learning Jason D. Williams and Geoffrey Zweig Microsoft Research One Microsoft Way, Redmond, WA 98052, USA {jason.williams,gzweig}@microsof Add to Reading List Source URL: arxiv.org Download Document from Source Website File Size: 1,28 MB Share Document on Facebook