| 2023 | EMNLP | DELPHI: Data for Evaluating LLMs' Performance in Handling Controversial Issues. | David Q. Sun, Artem Abzaliev, Hadas Kotek, Christopher Klein, Zidi Xiu, Jason D. Williams |
| 2023 | PAKDD | Feedback Effect in User Interaction with Intelligent Assistants: Delayed Engagement, Adaption and Drop-out. | Zidi Xiu, Kai-Chen Cheng, David Q. Sun, Jiannan Lu, Hadas Kotek, Yuhan Zhang, Paul McCarthy, Christopher Klein, Stephen Pulman, Jason D. Williams |
| 2021 | ICASSP | Generating Natural Questions from Images for Multimodal Assistants. | Alkesh Patel, Akanksha Bindal, Hadas Kotek, Christopher Klein, Jason D. Williams |
| 2021 | Interspeech | DEXTER: Deep Encoding of External Knowledge for Named Entity Recognition in Virtual Assistants. | Deepak Muralidharan, Joel Ruben Antony Moniz, Weicheng Zhang, Stephen Pulman, Lin Li, Megan Barnes, Jingjing Pan, Jason D. Williams, Alex Acero |
| 2021 | NAACL | Noise Robust Named Entity Understanding for Voice Assistants. | Deepak Muralidharan, Joel Ruben Antony Moniz, Sida Gao, Xiao Yang, Justine T. Kao, Stephen Pulman, Atish Kothari, Ray Shen, Yinying Pan, Vivek Kaul, Mubarak Seyed Ibrahim, Gang Xiang, Nan Dun, Yidan Zhou, Andy O, Yuan Zhang, Pooja Chitkara, Xuan Wang, Alkesh Patel, Kushal Tayal, Roger Zheng, Peter Grasch, Jason D. Williams, Lin Li |
| 2020 | COLING | Improving Human-Labeled Data through Dynamic Automatic Conflict Resolution. | David Q. Sun, Hadas Kotek, Christopher Klein, Mayank Gupta, William Li, Jason D. Williams |
| 2020 | EMNLP | Conversational Semantic Parsing for Dialog State Tracking. | Jianpeng Cheng, Devang Agrawal, Hctor Martnez Alonso, Shruti Bhargava, Joris Driesen, Federico Flego, Dain Kaplan, Dimitri Kartsaklis, Lin Li, Dhivya Piraviperumal, Jason D. Williams, Hong Yu, Diarmuid Saghdha, Anders Johannsen |
| 2020 | ICASSP | Lattice-Based Improvements for Voice Triggering Using Graph Neural Networks. | Pranay Dighe, Saurabh Adya, Nuoyu Li, Srikanth Vishnubhotla, Devang Naik, Adithya Sagar, Ying Ma, Stephen Pulman, Jason D. Williams |
| 2019 | Interspeech | Active Learning for Domain Classification in a Commercial Spoken Personal Assistant. | Xi C. Chen, Adithya Sagar, Justine T. Kao, Tony Y. Li, Christopher Klein, Stephen Pulman, Ashish Garg, Jason D. Williams |
| 2017 | ACL | Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning. | Jason D. Williams, Kavosh Asadi, Geoffrey Zweig |
| 2017 | SIGdial | Demonstration of interactive teaching for end-to-end dialog control with hybrid code networks. | Jason D. Williams, Lars Liden |
| 2015 | SP | Rapidly Scaling Dialog Systems with Interactive Learning. | Jason D. Williams, Nobal B. Niraula, Pradeep Dasigi, Aparna Lakshmiratan, Carlos Garcia Jurado Suarez, Mouni Reddy, Geoffrey Zweig |
| 2015 | SIGdial | Fast and easy language understanding for dialog systems with Microsoft Language Understanding Intelligent Service (LUIS). | Jason D. Williams, Eslam Kamal, Mokhtar Ashour, Hani Amr, Jessica Miller, Geoffrey Zweig |
| 2014 | ACL | Discovering Latent Structure in Task-Oriented Dialogues. | Ke Zhai, Jason D. Williams |
| 2014 | SIGdial | The Second Dialog State Tracking Challenge. | Matthew Henderson, Blaise Thomson, Jason D. Williams |
| 2014 | SIGdial | Web-style ranking and SLU combination for dialog state tracking. | Jason D. Williams |
| 2013 | ACL | Discriminative state tracking for spoken dialog systems. | Angeliki Metallinou, Dan Bohus, Jason D. Williams |
| 2013 | ICASSP | Recent advances in deep learning for speech research at Microsoft. | Li Deng, Jinyu Li, Jui-Ting Huang, Kaisheng Yao, Dong Yu, Frank Seide, Michael L. Seltzer, Geoffrey Zweig, Xiaodong He, Jason D. Williams, Yifan Gong, Alex Acero |
| 2013 | SIGdial | Continuously Predicting and Processing Barge-in During a Live Spoken Dialogue Task. | Ethan Selfridge, Iker Arizmendi, Peter A. Heeman, Jason D. Williams |
| 2013 | SIGdial | Multi-domain learning and generalization in dialog state tracking. | Jason D. Williams |
| 2013 | SIGdial | The Dialog State Tracking Challenge. | Jason D. Williams, Antoine Raux, Deepak Ramachandran, Alan W. Black |
| 2012 | NAACL | A belief tracking challenge task for spoken dialog systems. | Jason D. Williams |
| 2012 | SIGdial | Integrating Incremental Speech Recognition and POMDP-Based Dialogue Systems. | Ethan Selfridge, Iker Arizmendi, Peter A. Heeman, Jason D. Williams |
| 2011 | ASRU | Crowd-sourcing for difficult transcription of speech. | Jason D. Williams, I. Dan Melamed, Tirso Alonso, Barbara Hollister, Jay G. Wilpon |
| 2011 | SIGdial | Spoken Dialog Challenge 2010: Comparison of Live and Control Test Results. | Alan W. Black, Susanne Burger, Alistair Conkie, Helen Wright Hastie, Simon Keizer, Oliver Lemon, Nicolas Merigaud, Gabriel Parent, Gabriel Schubiner, Blaise Thomson, Jason D. Williams, Kai Yu, Steve J. Young, Maxine Esknazi |
| 2011 | SIGdial | Stability and Accuracy in Incremental Speech Recognition. | Ethan Selfridge, Iker Arizmendi, Peter A. Heeman, Jason D. Williams |
| 2011 | SIGdial | An Empirical Evaluation of a Statistical Dialog System in Public Use. | Jason D. Williams |
| 2010 | ICASSP | Incremental partition recombination for efficient tracking of multiple dialog states. | Jason D. Williams |
| 2009 | ASRU | Spoken dialogue systems: Challenges, and opportunities for research. | Jason D. Williams |
| 2009 | Interspeech | Reinforcement learning for dialog management using least-squares Policy iteration and fast feature selection. | Lihong Li, Jason D. Williams, Suhrid Balakrishnan |
| 2009 | SIGdial | Estimating Probability of Correctness for ASR N-Best Lists. | Jason D. Williams, Suhrid Balakrishnan |
| 2008 | ACL | Using Automatically Transcribed Dialogs to Learn User Models in a Spoken Dialog System. | Umar Syed, Jason D. Williams |
| 2008 | ACL | Demonstration of a POMDP Voice Dialer. | Jason D. Williams |
| 2008 | Interspeech | Exploiting the ASR n-best by tracking multiple dialog state hypotheses. | Jason D. Williams |
| 2008 | Interspeech | The best of both worlds: unifying conventional dialog systems and POMDPs. | Jason D. Williams |
| 2007 | ASRU | Using particle filters to track dialogue state. | Jason D. Williams |
| 2007 | ASRU | A method for evaluating and comparing user simulations: The Cramr-von Mises divergence. | Jason D. Williams |
| 2005 | SIGdial | Partially Observable Markov Decision Processes with Continuous Observations for Dialogue Management. | Jason D. Williams, Pascal Poupart, Steve J. Young |
| 2004 | Interspeech | A framework for dialogue data collection with a simulated ASR channel. | Matthew N. Stuttle, Jason D. Williams, Steve J. Young |
| 2004 | Interspeech | Characterizing task-oriented dialog using a simulated ASR chanel. | Jason D. Williams, Steve J. Young |
| 2003 | Interspeech | Preference, perception, and task completion of open, menu-based, and directed prompts for call routing: a case study. | Jason D. Williams, Andrew T. Shaw, Lawrence Piano, Michael Abt |
| 2003 | Interspeech | Two studies of open vs. directed dialog strategies in spoken dialog systems. | Silke M. Witt, Jason D. Williams |
| 2003 | SIGdial | Using Wizard-of-Oz simulations to bootstrap Reinforcement - Learning based dialog management systems. | Jason D. Williams, Steve J. Young |