Cynthia Matuszek

Affiliated Faculty, Faculty
My primary research interests are in robotics and natural language processing; in my work, I combine these interests to support research in human-robot interaction, or HRI. My work focuses on the problem of grounded language acquisition: extracting semantically meaningful representations of human language by mapping those representations to the noisy, unpredictable physical world in which robots operate. More specifically, I work on combining probabilistic, grammar-based natural language processing with machine learning to transform human communication into a formal language that a robot can understand. I have looked at using this kind of language learning to learn how to follow navigation instructions or learn more about the world from human users by learning to extend a world model in tandem with learning a language parsing model.
Refereed Publications
2020
- N. W. Pillai, E. Raff, F. Ferraro, and C. Matuszek, "Sampling Approach Matters: Active Learning for Robotic Language Acquisition", InProceedings, IEEE BigData BDML, December 2020, 17 downloads.
- A. T. Nguyen, L. E. Richards, G. Y. Kebe, E. Raff, K. Darvish, F. Ferraro, and C. Matuszek, "Practical Cross-modal Manifold Alignment for Grounded Language", Article, arXiv:2009.05147 [cs.CV], September 2020, 32 downloads.
- P. Jenkins, R. Sachdeva, G. Y. Kebe, P. Higgins, K. Darvish, E. Raff, D. Engel, J. Winder, F. Ferraro, and C. Matuszek, "Presentation and Analysis of a Multimodal Dataset for Grounded Language Learning", Article, arXiv:2007.14987 [cs.RO], July 2020, 35 downloads.
2019
- C. Kery, N. W. Pillai, C. Matuszek, and F. Ferraro, "Building Language-Agnostic Grounded Language Learning Systems", InProceedings, 28th International Conference on Robot and Human Interactive Communication (Ro-Man), October 2019, 78 downloads.
- M. Murnane, M. Breitmeyer, F. Ferraro, C. Matuszek, and D. Engel, "Learning from Human-Robot Interactions in Modeled Scenes", InProceedings, ACM SIGGRAPH 2019 Posters, July 2019, 53 downloads.
- M. Murnane, M. Breitmeyer, F. Ferraro, and C. Matuszek, "Learning from Human-Robot Interactions in Modeled Scenes", InProceedings, ACM SIGGRAPH 2019 Posters, July 2019, 60 downloads.
- C. Kery, F. Ferraro, and C. Matuszek, "¿Es un plátano? Exploring the Application of a Physically Grounded Language Acquisition System to Spanish", NAACL Combined Workshop on Spatial Language Understanding and Grounded Communication for Robotics, June 2019, 149 downloads.
- N. W. Pillai, F. Ferraro, and C. Matuszek, "Deep Learning for Category-Free Grounded Language Acquisition", NAACL Workshop on Spatial Language Understanding and Grounded Communication for Robotics, June 2019, 45 downloads.
2018
- N. W. Pillai, F. Ferraro, and C. Matuszek, "Optimal Semantic Distance for Negative Example Selection in Grounded Language Acquisition", Workshop on Models and Representations for Natural Human-Robot Communication (Robotics: Science and Systems), June 2018, 136 downloads.
2016
- P. K. Das, A. L. Kashyap, G. Singh, C. Matuszek, T. Finin, and A. Joshi, "Semantic knowledge and privacy in the physical web", InProceedings, Proceedings of the 4th Workshop on Society, Privacy and the Semantic Web - Policy and Technology (PrivOn2016) co-located with 15th International Semantic Web Conference (ISWC 2016), October 2016, 1732 downloads.