William P. Li
Hello world! I am a Machine Learning Engineering Manager at Apple in Cupertino, CA. Currently, I lead a team in Siri that researches, builds, and ships natural language understanding (NLU) features, models, and systems for billions of devices and users.
I completed my PhD in Electrical Engineering and Computer Science at MIT in the Computer Science and Artificial Intelligence Laboratory (CSAIL) and the Laboratory for Financial Engineering. My advisor was Andrew Lo. I was also a Fellow and Affiliate at the Harvard University Berkman-Klein Center for Internet and Society, focusing on artificial intelligence and open government datasets.
My doctoral research focused on language technologies for understanding law, politics, and public policy. Specifically, I developed machine learning techniques for large collections of legal and political documents. This work offers new ways to answer research questions in law, politics, and public policy, from the authorship of Supreme Court opinions to the structure and evolution of our laws. I aimed to develop techniques that 1) help citizens understand government processes and 2) help governments and policymakers understand large collections of public political speech. Check out my thesis defense slides for an overview of this work (or my entire PhD dissertation if you'd like!)
I am also passionate about the fields of assistive technology and accessibility. I have conducted research, taught classes, and built community efforts around assistive technology, accessibility, disability, and inclusion, working collaboratively with people with disabilities to develop technologies that increase independence and broaden participation.
Previously, I earned master's degrees at MIT in computer science and the Technology and Policy Program. My advisors were Seth Teller, Nicholas Roy, and Jim Glass, and I focused on natural language understanding in spoken dialogue systems and assistive technology. As an undergraduate, I was an Engineering Science student at the University of Toronto, and grew up in Mississauga, Ontario, Canada.
Language Technologies for Understanding Law, Politics, and Public Policy
Li, W., Azar, P., Larochelle, D., Hill, P., Lo, A.W. Law Is Code: A Software Engineering Approach to Analyzing the United States Code. Journal of Business and Technology Law, 10, 297, 2015.
Chuang, J.*, Fish, S.*, Larochelle, D.*, Li, W.*, Weiss, R.* Large-Scale Topical Analysis of Multiple Online News Sources with Media Cloud. NewsKDD, August 2014.
Chou, S.*, Li, W.*, Sridharan, R.* Democratizing Data Science. KDD at Bloomberg, August 2014.
Li, W., Larochelle, D., Lo, A. W. Estimating Policy Trajectories During the Financial Crisis. NLP Unshared Task in PoliInformatics, June 2014.
Li, W., Azar, P., Larochelle, D., Hill, P., Cox, J., Berwick, R. C., Lo, A. W. Using Algorithmic Attribution Techniques to Determine Authorship in Unsigned Judicial Opinions. Stanford Technology Law Review, 16, 503-533, June 2013.
Healthcare Systems and Assistive Technologies
Doshi-Velez, F.*, Li, W.*, Battat, Y., Park, J., Charrow, B., Curtis, D., Hemachandra, S., Reimer, B., Velez, J., Walsh, C., Fredette, D., Roy, N., Teller, S. Improving Safety and Operational Efficiency in Residential Care Settings with WiFi-based Localization. Journal of the American Medical Directors Association (JAMDA), July 2012.
Li, W., Lam-Damji, S., Chau, T., and Fehlings, D. The development of a home-based virtual reality therapy system to promote upper extremity movement for children with hemiplegic cerebral palsy. Technology and Disability. 21(3): 2009.
Undergraduate thesis: Development and evaluation of a virtual reality therapy system for children with hemiplegic cerebral palsy, 2008.
Li, W., Lam-Damji, S., Chau, T., and Fehlings, D. Usability of a virtual reality therapy system for children with hemiplegic cerebral palsy, Proceedings of the 30th Canadian Medical and Biological Engineering Conference, Toronto, 2007.
Speech Processing and Dialogue Systems
Li, W., Glass, J., Roy, N., Teller, S. Probabilistic Dialogue Modeling for Speech-Enabled Assistive Technology, Proceedings of the 4th Workshop on Speech and Language Processing for Assistive Technologies (SLPAT), Grenoble, August 2013.
Li, W., Fredette, D., Burnham, A., Lamoureux, B., Serotkin, M., Teller, S. Making Speech-Based Assistive Technology Work for a Real User, Proceedings of the 4th Workshop on Speech and Language Processing for Assistive Technologies (SLPAT), Grenoble, August 2013.
Master's thesis: Understanding User State and Preferences for Robust Spoken Dialog Systems and Location-Aware Assistive Technology, 2012.
Assistive Technology Economics
Li, W. and Sellers, C. Improving assistive technology economics for people with disabilities: harnessing the voluntary and education sectors, Proceedings of IEEE Toronto International Conference on Science, Technology, and Humanity, Toronto, 2009.
Li, W. Student-based models for tiny-market assistive technologies: Early experiences and lessons learned, Association for the Advancement of Assistive Technology in Europe (AAATE) -- AT Technology Transfer Workshop, Sheffield, 2010.
Projects and Activities
Founded in 2011, the MIT Assistive Technology Club is a MIT student group that serves as the starting point for engaging with students, faculty, and staff about assistive technology (AT) for people with disabilities.
David Kwabi and I co-organized the 2011-2012 S-P Distinguished Lecture Series, which brings speakers to Sidney Pacific for a public lecture and dinner with students.