Timezone: »

Latent Intention Dialogue Models
Tsung-Hsien Wen · Yishu Miao · Phil Blunsom · Stephen J Young

Tue Aug 08 08:30 PM -- 08:48 PM (PDT) @ Parkside 1

Developing a dialogue agent that is capable of making autonomous decisions and communicating by natural language is one of the long-term goals of machine learning research. The traditional approaches either rely on hand-crafting a small state-action set for applying reinforcement learning that is not scalable or constructing deterministic models for learning dialogue sentences that fail to capture the conversational stochasticity. In this paper, however, we propose a Latent Intention Dialogue Model that employs a discrete latent variable to learn underlying dialogue intentions in the framework of neural variational inference. Additionally, in a goal-oriented dialogue scenario, the latent intentions can be interpreted as actions guiding the generation of machine responses, which can be further refined autonomously by reinforcement learning. The experiments demonstrate the effectiveness of discrete latent variable models on learning goal-oriented dialogues, and the results outperform the published benchmarks on both corpus-based evaluation and human evaluation.

Author Information

Tsung-Hsien Wen (University of Cambridge)
Yishu Miao (University of Oxford)
Philip Blunsom (Oxford University and DeepMind)
Steve Young J Young (University of Cambridge)

Steve Young is Professor of Information Engineering in the Information Engineering Division. His main research interests lie in the area of spoken language systems including speech recognition, speech synthesis and dialogue management. He was Editor of Computer Speech and Language from 1993 to 2004, and Chair of the IEEE Speech and Language Processing Technical Committee from 2009 to 2011. He now holds a joint appointment between Cambridge University and Apple Computer where he is a member of the Siri Development Team. Steve is a Fellow of the Royal Academy of Engineering, the Institution of Engineering and Technology (IET), the Institute of Electrical and Electronics Engineers (IEEE) and the RSA. In 2004, he was a recipient of an IEEE Signal Processing Society Technical Achievement Award; in 2008 he was elected Fellow of the International Speech Communication Association (ISCA) ; in 2010, he received the ISCA Medal for Scientific Achievement ; in 2013, he received the European Signal Processing Society Individual Technical Achievement Award ; and in 2015 he received the IEEE James L Flanagan Speech and Audio Processing Award.

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors