Boris Katz

Boris Katz
Boris
Katz
Coordinator for Technology and Knowledge Transfer, Research Module Co-Leader

Associated Research Module: 

Associated Research Thrust: 

Boris Katz is a Principal Research Scientist and Head of the InfoLab Group at MIT’s Computer Science and Artificial Intelligence Laboratory. His research interests include natural language understanding and generation, intelligent information access, knowledge representation, human computer interaction, and event recognition.

Boris Katz is the creator of the START information access system and the inventor of a patented method of natural language annotations, which facilitate access to multimedia information in response to questions expressed in everyday language. In 1989 during the Voyager Neptune encounter, START was used in the JPL press room to answer reporters’ questions about the Voyager 2 spacecraft. In 1993, START became the first question-answering system on the Web, and since then answered millions of questions from Web users all over the world.

Boris Katz is a member of the Open Advancement of Question Answering consortium where he contributed several technical ideas incorporated into IBM’s Watson system, which in 2011 defeated the all-time human champions on the quiz show Jeopardy. Technology created in Katz's InfoLab Group in 2006 (see press, technical paper and video) was a major inspiration for the development of Apple's personal assistant, Siri.

 

Current Advisees

Julian Alverio - Graduate Research Assistant
Andrei Barbu - Research Scientist
Yen-Ling Kuo - Graduate Student
Xin Yu Lin - Graduate Student
Natasha Maniar - Undergraduate , UROP
Aviv Netanyahu - Graduate Student
Dana Rosenfarb - Graduate Student
Lucia Schiatti - Postdoc
Aaditya K. Singh - Graduate Student
Vighnesh Subramaniam - Research Assistant
Ravi Tejwani - Graduate Student

Past Advisees

Dalitso Banda - Research Assistant
Guy Ben-Yosef - Research Scientist
Yevgeni Berzak - Graduate Student
Run Chen - Undergraduate Researcher
Allison Fu - Graduate Student
Lila Jansen - UROP
Jonathan Malmaud - Graduate Student
Cheahuychou Mao - Graduate Student
Cristina Mata - Graduate Student
David Mayo - Graduate Student
Sangeev Murty - Graduate Student
Candace Ross - Graduate Student
Amelia Smith - Undergraduate Researcher
Carrie Spadine - Graduate Student
Dalila Stanfield - Undergraduate Researcher
Adam Yaari - Graduate Student

Projects

CBMM Publications

C. Wang, Subramaniam, V., Yaari, A. Uri, Kreiman, G., Katz, B., Cases, I., and Barbu, A., BrainBERT: Self-supervised representation learning for Intracranial Electrodes, International Conference on Learning Representations. Kigali, Rwanda, Africa, 2023.
A. Yaari, DeWitt, J., Hu, H., Stankovits, B., Felshin, S., Berzak, Y., Aparicio, H., Katz, B., Cases, I., and Barbu, A., The Aligned Multimodal Movie Treebank: An audio, video, dependency-parse treebank, in Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022.
C. Ross, Katz, B., and Barbu, A., Measuring Social Biases in Grounded Vision and Language Embeddings, NAACL (Annual Conference of the North American Chapter of the Association for Computational Linguistics). 2021.
A. Netanyahu, Shu, T., Katz, B., Barbu, A., and Tenenbaum, J. B., PHASE: PHysically-grounded Abstract Social Eventsfor Machine Social Perception, in Shared Visual Representations in Human and Machine Intelligence (SVRHM) workshop at NeurIPS 2020, 2020.
C. Ross, Berzak, Y., Katz, B., and Barbu, A., Learning Language from Vision., in Workshop on Visually Grounded Interaction and Language (ViGIL) at the Thirty-third Annual Conference on Neural Information Processing Systems (NeurIPS), Vancouver Convention Center, Vancouver, Canada, 2019.
B. Katz, Borchardt, G., Felshin, S., and Mora, F., A Natural Language Interface for Mobile Devices, in The Wiley Handbook of Human Computer Interaction, First., vol. 2, John Wiley & Sons , 2018, pp. 539-559.
Y. Berzak, Katz, B., and Levy, R., Assessing Language Proficiency from Eye Movements in Reading, 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. New Orleans, 2018.
Y. - L. Kuo, Barbu, A., and Katz, B., Deep sequential models for sampling-based planning, in The IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2018), Madrid, Spain, 2018.
C. Ross, Barbu, A., Berzak, Y., Myanganbayar, B., and Katz, B., Grounding language acquisition by training semantic parsersusing captioned videos, in Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP 2018), , Brussels, Belgium, 2018.
Y. Berzak, Nakamura, C., Flynn, S., and Katz, B., Predicting Native Language from Gaze, in Annual Meeting of the Association for Computational Linguistics (ACL 2017), 2017.
R. Paul, Barbu, A., Felshin, S., Katz, B., and Roy, N., Temporal Grounding Graphs for Language Understanding with Accrued Visual-Linguistic Context, in Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI 2017), Melbourne, Australia, 2017.
A. Morales, Premtoon, V., Avery, C., Felshin, S., and Katz, B., Learning to Answer Questions from Wikipedia Infoboxes, in The 2016 Conference on Empirical Methods on Natural Language Processing (EMNLP 2016), 2016.
Y. Berzak, Reichart, R., and Katz, B., Contrastive Analysis with Predictive Power: Typology Driven Estimation of Grammatical Error Distributions in ESL, in Nineteenth Conference on Computational Natural Language Learning (CoNLL), Beijing, China, 2015.
Y. Berzak, Barbu, A., Harari, D., Katz, B., and Ullman, S., Do You See What I Mean? Visual Resolution of Linguistic Ambiguities, in Conference on Empirical Methods in Natural Language Processing, Lisbon, Portugal. , 2015.