Invited Speakers
Pascale Fung
Pascale Fung is a Professor at the Department of Electronic & Computer Engineering at The Hong Kong University of Science & Technology. She is an elected Fellow of the Institute of Electrical and Electronic Engineers (IEEE) and Fellow of the International Speech Communication Association. She co-founded the Human Language Technology Center (HLTC) at HKUST and is an affiliated faculty with both the Robotics Institute and the Big Data Institute. She is the founding chair of the Women Faculty Association at HKUST. Pascale’s research interests lie primarily in building intelligent systems that can understand and empathize with humans, enabled by spoken language understanding, speech, facial expression, and sentiment recognition. She is blogs for the World Economic Forum on societal impacts of spoken language processing and machine learning. She is a member of the Global Future Council on AI and Robotics of the World Economic Forum.
Invited talk: 15:55-16h30 Empathetic Natural Language Processing
It has been shown that humans need to establish rapport with each other and with machines to achieve effective communication. Establishing rapport includes the ability to recognize different emotions, and understand other high level communication features such as humor, sarcasm and intent. In order to make such communication possible, machines need to extract emotions from human speech and behavior and can accordingly decide the emotionally correct response. In this talk, I will give an overview of multi-channel recognition and expression of speech and language with emotion and intent. I will present the kind of fundamental questions we ask in R&D of empathetic machines, and our work so far in the areas of deep learning of emotion and sentiment recognition. I hope to explore the future direction of virtual agents and robot development and how it can help improve people’s lives.
Ndapa Nakashole
Ndapa studies the problem of systems that learn to read and understand language.
A research thrust she has recently begun exploring is NLP for languages with millions of speakers but very few, if any, NLP tools.
Invited talk: 11:00-11:35 Improving zero-shot learning for word-level translation
Zero-shot learning is used in computer vision, natural language, and other domains to induce mapping functions that project vectors from one vector space to another. This is a promising approach to learning when we do not have labeled data for every possible label we want a system to recognize. This setting is common when doing NLP for low-resource languages, where labeled data is very scare. In this talk, I will present our work on improving zero-shot learning methods for the task of word-level translation.
Bonnie Webber
Bonnie studies discourse phenomena in language and statistical models. Her research examines the role that context plays in determining different discourse structures, and the role that discourse plays in statistical machine translation.
Invited talk: 09:00-09:35 Discourse and Computation: A life in tokens
Back in the 70s, I was enrolled as a part-time PhD student at Harvard. Three years into the programme, I was invited to either submit a thesis proposal or leave. At the time, I was working at Bolt Beranek and Newman (BBN), and so I asked my colleagues what I should do. As my job involved semantic interpretation for Question-Answering systems, including anaphor resolution, I was advised to just come up with some examples that systems couldn’t handle and figure out what was needed to handle them. Thus was born my PhD proposal, a paper for COLING, and my subsequent “life in tokens”. In this talk, I’ll go through some of the many of the tokens I identified as presenting challenges to the systems of the day (and even to some today).