Deep Learning for Dialogue Systems

9 aprile 2018
10 aprile 2018
9 e 10 aprile 2018

1st Lecture on April 9 @ 2:30 - 4:30  pm, Via Sommarive 9: Polo Ferrari 2 - Room B103

2nd Lecture on April 10 @ 9:30 - 11:30 am, Via Sommarive 5: Polo Ferrari 1 - Room A203

Speaker

  • Dilek Hakkani-Tür, Google Research, USA

Abstract

Goal-oriented spoken dialogue systems have been the most prominent component in today’s virtual personal assistants (VPAs).  These aim to allow users to speak naturally in order to finish tasks more efficiently. Traditional conversational systems have rather complex and/or modular pipelines. The advance of deep learning technologies has recently resulted in application of neural models to dialogue modeling. Nevertheless, applying deep learning technologies for building robust and scalable dialogue systems is still a challenging task and an open research area, as it requires deeper understanding of the classic pipelines, a detailed knowledge of the component models, the prior work and the recent state-of-the-art. This tutorial is designed to present an overview of dialogue system development while describing recent research for building dialogue systems, and summarizing the challenges. 

About the Speaker

Dilek Hakkani-Tür is a research scientist at Google leading the dialogue research team. Prior to joining Google, she was a principal researcher at Microsoft Research (2010-2016), International Computer Science Institute (ICSI, 2006-2010) and AT&T Labs-Research (2001-2005). She received her BSc degree from Middle East Technical Univ, in 1994, and MSc and PhD degrees from Bilkent Univ., Department of Computer Engineering, in 1996 and 2000, respectively.

Her research interests include conversational AI, natural language and speech processing, spoken dialogue systems, and machine learning for language processing. She has over 65 patents that were granted and co-authored more than 200 papers in natural language and speech processing. She is the recipient of three best paper awards for her work on active learning for dialogue systems, from IEEE Signal Processing Society, ISCA and EURASIP. She was an associate editor of IEEE Transactions on Audio, Speech and Language Processing (2005-2008), member of the IEEE Speech and Language Technical Committee (2009-2014), area editor for speech and language processing for Elsevier's Digital Signal Processing Journal and IEEE Signal Processing Letters (2011-2013), and currently serves on ISCA Advisory Council (2015-2019). She is a fellow of IEEE and ISCA.

Contact Person for this Seminar: giuseppe.riccardi [at] unitn.it (Giuseppe Riccardi)