Stéphane T. Aroca-Ouellette

University of Colorado Boulder, stephane.aroca-ouellette@colorado.edu .

I am a first year PhD student trying to discover how the interplay of NLP and robotics can mutually benefit both fields. I am co-advised by Alessandro Roncone as part of the HIRO group and by Katharina Kann as part of the NALA group. Prior to CU Boulder, I completed both my bachelors of applied science in computer engineering and my masters of computer science at the University of Toronto under Frank Rudzicz with a focus on NLP. Currently trying to find ther right balance between refreshing 3090 stocks and climbing.


Research Direction:

Natural language is the easiest and most generalizable way for humans to specify a task, provide new information, and convey intentions. Achieving this communication with robots requires grounding language to the world that they exist in. More concretely, this requires enabling robots to map words and phrases to objects, actions, and concepts. To this end, we are investigating how to condition robotic motion on natural language with the aim of developing a more flexible and generalizable task specification framework. Further, we are interested in how real-world experience changes a model’s interpretation of language.

Selected Publications:

  1. On Losses for Modern Language Models
    Aroca-Ouellette, Stéphane, and Rudzicz, Frank
    In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) 2020