Dr. Dilek Hakkani-Tür of Amazon

Previous work on task-oriented dialogue systems are usually restricted to a limited coverage of APIs related to the set of tasks considered in the application domain. However, users oftentimes have domain related requests that are not covered by these APIs, even for their task-focused intents. To enable natural interactions with machines, we propose to expand the coverage of task-oriented dialogue systems by incorporating external, unstructured knowledge sources, such as web documents related to the task domain. In this talk, after a brief overview of dialogue systems research, I’ll present how we integrate knowledgeable responses into task-oriented conversations, and summarize our learnings from our work as well as public challenges we've been organizing in this area.

Biography:

Dilek Hakkani-Tür is a senior principal scientist at Amazon Alexa AI focusing on enabling natural dialogues with machines and a Visiting Distinguished Professor at UC Santa Cruz. Prior to joining Amazon, she was a researcher at Google, Microsoft Research, International Computer Science Institute and AT&T Labs-Research. She received her BSc degree from Middle East Technical Univ. and MSc and PhD degrees from Bilkent Univ. in Computer Science. Her research interests include conversational AI, natural language and speech processing, spoken dialogue systems, and machine learning for language processing. She has over 80 patents and co-authored more than 300 papers in natural language and speech processing. Her work received several best paper awards (including from IEEE Signal Processing Society, ISCA and EURASIP.) She is currently the Editor-in-Chief of the IEEE/ACM Transactions on Audio, Speech and Language Processing, an IEEE Distinguished Industry Speaker (2021) and a fellow of the IEEE and ISCA.

Dr. Hakkani-Tür is the recipient of three best paper awards for her work on active learning for dialogue systems, from IEEE Signal Processing Society (2008), International Symposium on Computer Architecture (ISCA) (2007) and European Association for Signal Processing (EURASIP) (2007). She served as Associate Editor, IEEE Transactions on Audio, Speech and Language Processing (2005-2008), Member, IEEE Speech and Language Processing 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 served on the ISCA Advisory Council (2015-2018). She is Editor-in-Chief, IEEE/ACM Transactions on Audio, Speech and Language Processing (2019-2021), and a Fellow of the IEEE (2014) and ISCA (2014).

 Dr. Hakkani-Tür’s research interests include conversational AI, natural language and speech processing, spoken dialogue systems, and machine learning for language processing.

Email: