Zobrazeno 1 - 10
of 30
pro vyhledávání: '"Bonial, Claire"'
Autor:
Lukin, Stephanie M., Bonial, Claire, Marge, Matthew, Hudson, Taylor, Hayes, Cory J., Pollard, Kimberly A., Baker, Anthony, Foots, Ashley N., Artstein, Ron, Gervits, Felix, Abrams, Mitchell, Henry, Cassidy, Donatelli, Lucia, Leuski, Anton, Hill, Susan G., Traum, David, Voss, Clare R.
Publikováno v:
2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024) https://aclanthology.org/2024.lrec-main.1259/
We introduce the Situated Corpus Of Understanding Transactions (SCOUT), a multi-modal collection of human-robot dialogue in the task domain of collaborative exploration. The corpus was constructed from multiple Wizard-of-Oz experiments where human pa
Externí odkaz:
http://arxiv.org/abs/2411.12844
Autor:
Bonial, Claire, Lukin, Stephanie M., Abrams, Mitchell, Baker, Anthony, Donatelli, Lucia, Foots, Ashley, Hayes, Cory J., Henry, Cassidy, Hudson, Taylor, Marge, Matthew, Pollard, Kimberly A., Artstein, Ron, Traum, David, Voss, Clare R.
Publikováno v:
Language Resources and Evaluation 2024
In this paper, we describe the development of symbolic representations annotated on human-robot dialogue data to make dimensions of meaning accessible to autonomous systems participating in collaborative, natural language dialogue, and to enable comm
Externí odkaz:
http://arxiv.org/abs/2411.12829
Autor:
Lukin, Stephanie M., Pollard, Kimberly A., Bonial, Claire, Hudson, Taylor, Arstein, Ron, Voss, Clare, Traum, David
Publikováno v:
Proceedings of the 2023 IEEE Robot and Human Interactive Communication Conference
Human-guided robotic exploration is a useful approach to gathering information at remote locations, especially those that might be too risky, inhospitable, or inaccessible for humans. Maintaining common ground between the remotely-located partners is
Externí odkaz:
http://arxiv.org/abs/2310.17568
Autor:
Goyal, Navita, Briakou, Eleftheria, Liu, Amanda, Baumler, Connor, Bonial, Claire, Micher, Jeffrey, Voss, Clare R., Carpuat, Marine, Daumé III, Hal
NLP systems have shown impressive performance at answering questions by retrieving relevant context. However, with the increasingly large models, it is impossible and often undesirable to constrain models' knowledge or reasoning to only the retrieved
Externí odkaz:
http://arxiv.org/abs/2305.14331
We describe the task of Visual Understanding and Narration, in which a robot (or agent) generates text for the images that it collects when navigating its environment, by answering open-ended questions, such as 'what happens, or might have happened,
Externí odkaz:
http://arxiv.org/abs/1906.00038
Autor:
Marge, Matthew, Bonial, Claire, Lukin, Stephanie, Hayes, Cory, Foots, Ashley, Artstein, Ron, Henry, Cassidy, Pollard, Kimberly, Gordon, Carla, Gervits, Felix, Leuski, Anton, Hill, Susan, Voss, Clare, Traum, David
We describe a multi-phased Wizard-of-Oz approach to collecting human-robot dialogue in a collaborative search and navigation task. The data is being used to train an initial automated robot dialogue system to support collaborative exploration tasks.
Externí odkaz:
http://arxiv.org/abs/1810.02017
Autor:
Lukin, Stephanie M., Pollard, Kimberly A., Bonial, Claire, Marge, Matthew, Henry, Cassidy, Arstein, Ron, Traum, David, Voss, Clare R.
This paper identifies stylistic differences in instruction-giving observed in a corpus of human-robot dialogue. Differences in verbosity and structure (i.e., single-intent vs. multi-intent instructions) arose naturally without restrictions or prior g
Externí odkaz:
http://arxiv.org/abs/1807.08076
Many previous methods have demonstrated the importance of considering semantically relevant objects for carrying out video-based human activity recognition, yet none of the methods have harvested the power of large text corpora to relate the objects
Externí odkaz:
http://arxiv.org/abs/1805.01818
Autor:
Bonial, Claire, Marge, Matthew, artstein, Ron, Foots, Ashley, Gervits, Felix, Hayes, Cory J., Henry, Cassidy, Hill, Susan G., Leuski, Anton, Lukin, Stephanie M., Moolchandani, Pooja, Pollard, Kimberly A., Traum, David, Voss, Clare R.
We describe the adaptation and refinement of a graphical user interface designed to facilitate a Wizard-of-Oz (WoZ) approach to collecting human-robot dialogue data. The data collected will be used to develop a dialogue system for robot navigation. B
Externí odkaz:
http://arxiv.org/abs/1710.06406
Autor:
Marge, Matthew, Bonial, Claire, Byrne, Brendan, Cassidy, Taylor, Evans, A. William, Hill, Susan G., Voss, Clare
Our overall program objective is to provide more natural ways for soldiers to interact and communicate with robots, much like how soldiers communicate with other soldiers today. We describe how the Wizard-of-Oz (WOz) method can be applied to multimod
Externí odkaz:
http://arxiv.org/abs/1703.03714