Raymond J. Mooney, University of Texas
Title: Dialog with Robots: Perceptually Grounded Communication with Lifelong Learning
Abstract: Developing robots that can accept instructions from and collaborate with human users is greatly enhanced by an ability to engage in natural language dialog. Unlike most other dialog scenarios, this requires grounding the semantic analysis of language in perception and action in the world. Although deep-learning has greatly enhanced methods for such grounded language understanding, it is difficult to ensure that the data used to train such models covers all of the concepts that a robot might encounter in practice. Therefore, we have developed methods that can continue to learn from dialog with users during ordinary use by acquiring additional targeted training data from the responses to intentionally designed clarification and active learning queries. These methods use reinforcement learning to automatically acquire dialog strategies that support both effective immediate task completion as well as learning that improves future performance. Using both experiments in simulation and with real robots, we have demonstrated that these methods exhibit life-long learning that improves long-term performance.
Bio: Raymond J. Mooney is a Professor in the Department of Computer Science at the University of Texas at Austin. He received his Ph.D. in 1988 from the University of Illinois at Urbana/Champaign. He is an author of over 180 published research papers, primarily in the areas of machine learning and natural language processing. He was the President of the International Machine Learning Society from 2008-2011, program co-chair for AAAI 2006, general chair for HLT-EMNLP 2005, and co-chair for ICML 1990. He is a Fellow of AAAI, ACM, and ACL and the recipient of the Classic Paper award from AAAI-19 and best paper awards from AAAI-96, KDD-04, ICML-05 and ACL-07.
Jason Weston, Facebook AI & NYU Visiting Research Professor
Title: A journey from ML & NNs to NLP and Beyond: Just more of the same isn’t enough?
Abstract: The first half of the talk will look back on the last two decades of machine learning, neural network and natural language processing research for dialogue, through my personal lens, to discuss the advances that have been made and the circumstances in which they happened — to try to give clues of what we should be working on for the future. The second half will dive deeper into some current first steps in those future directions, in particular trying to fix the problems of neural generative models to enable deeper reasoning with short and long-term coherence, and to ground such dialogue agents to an environment where they can act and learn. We will argue that just scaling up current techniques, while a worthy investigation, will not be enough to solve these problems.
Bio: Jason Weston is a research scientist at Facebook, NY and a Visiting Research Professor at NYU. He earned his PhD in machine learning at Royal Holloway, University of London and at AT&T Research in Red Bank, NJ (advisors: Alex Gammerman, Volodya Vovk and Vladimir Vapnik) in 2000. From 2000 to 2001, he was a researcher at Biowulf technologies. From 2002 to 2003 he was a research scientist at the Max Planck Institute for Biological Cybernetics, Tuebingen, Germany. From 2003 to 2009 he was a research staff member at NEC Labs America, Princeton. From 2009 to 2014 he was a research scientist at Google, NY. His interests lie in statistical machine learning, with a focus on reasoning, memory, perception, interaction and communication. Jason has published over 100 papers, including best paper awards at ICML and ECML, and a Test of Time Award for his work “A Unified Architecture for Natural Language Processing: Deep Neural Networks with Multitask Learning”, ICML 2008 (with Ronan Collobert). He was part of the YouTube team that won a National Academy of Television Arts & Sciences Emmy Award for Technology and Engineering for Personalized Recommendation Engines for Video Discovery. He was listed as the 16th most influential machine learning scholar at AMiner and one of the top 50 authors in Computer Science in Science.
Julia Hirschberg, Columbia University
Title: Whom Do We Trust in Dialogue Systems?
Abstract: It is important for computer systems today to encourage user trust: for recommender systems, knowledge-delivery systems, and dialogue systems in general. What aspects of text or speech production do humans tend to trust? It is also important for these systems to be able to identify whether in fact a user does trust them. But producing trusted speech and recognizing user trust are still challenging questions. Our work on trusted and mistrusted speech has produced some useful information about the first issue, exploring the types of lexical and acoustic-prosodic features in human speech that listeners tend to trust or to mistrust. Using the very large Columbia Cross-cultural Deception Corpus we created to detect truth vs. lie, we created a LieCatcher game to crowd-source a project on trusted vs. mistrusted speech from multiple raters listening to question responses and rating them as true or false. We present results on the types of speech raters trusted or did not trust and their reasoning behind their answers. We then describe ongoing research on the second issue: How do we determine whether a user trusts the system and do aspects of their speech reveal useful information?
Bio: Julia Hirschberg is Percy K. and Vida L. W. Hudson Professor of Computer Science at Columbia University. She previously worked at Bell Laboratories and AT&T Labs on text-to-speech synthesis (TTs) and created their first HCI Research Department. She is a fellow of AAAI, ISCA, ACL, ACM, and IEEE, and a member of the NAE, the American Academy of Arts and Sciences, and the American Philosophical Society, and has received the IEEE James L. Flanagan Speech and Audio Processing Award, the ISCA Medal for Scientific Achievement and the ISCA Special Service Medal. She studies speech and NLP, currently TTS; deceptive, trusted, emotional, and charismatic speech; false information and intent on social media; multimodal humor; and radicalization. She has worked for diversity for many years at AT&T and Columbia.