What's in a Gaze? The Role of Eye-Gaze in Reference Resolution in Multimodal Conversational Interfaces
Z. Prasov, and J. Chai. Proceedings of IUI '08: 13th International Conference on Intelligent User Interfaces, Gran Canaria, Spain, page 20-29. (2008)
DOI: 10.1145/1378773.1378777
Abstract
Multimodal conversational interfaces allow users to carry a dialog with a graphical display using speech to accomplish a particular task. Motivated by previous psycholinguistic findings, we examine how eye-gaze contributes to reference resolution in such a setting. Specifically, we present an integrated probabilistic framework that combines speech and eye-gaze for reference resolution. We further examine the relationship between eye-gaze and increased domain modeling with corresponding linguistic processing. Our empirical results show that the incorporation of eye-gaze significantly improves reference resolution performance. This improvement is most dramatic when a simple domain model is used. Our results also show that minimal domain modeling combined with eye-gaze significantly outperforms complex domain modeling without eye-gaze, which indicates that eye-gaze can be used to potentially compensate a lack of domain modeling for reference resolution.
%0 Conference Paper
%1 PrasovChai08IUI
%A Prasov, Zahar
%A Chai, Joyce Y.
%B Proceedings of IUI '08: 13th International Conference on Intelligent User Interfaces, Gran Canaria, Spain
%D 2008
%K v1205 acm paper ai user interface multimodal interaction language processing video analysis
%P 20-29
%R 10.1145/1378773.1378777
%T What's in a Gaze? The Role of Eye-Gaze in Reference Resolution in Multimodal Conversational Interfaces
%X Multimodal conversational interfaces allow users to carry a dialog with a graphical display using speech to accomplish a particular task. Motivated by previous psycholinguistic findings, we examine how eye-gaze contributes to reference resolution in such a setting. Specifically, we present an integrated probabilistic framework that combines speech and eye-gaze for reference resolution. We further examine the relationship between eye-gaze and increased domain modeling with corresponding linguistic processing. Our empirical results show that the incorporation of eye-gaze significantly improves reference resolution performance. This improvement is most dramatic when a simple domain model is used. Our results also show that minimal domain modeling combined with eye-gaze significantly outperforms complex domain modeling without eye-gaze, which indicates that eye-gaze can be used to potentially compensate a lack of domain modeling for reference resolution.
%@ 978-1-59593-987-6
@inproceedings{PrasovChai08IUI,
abstract = {Multimodal conversational interfaces allow users to carry a dialog with a graphical display using speech to accomplish a particular task. Motivated by previous psycholinguistic findings, we examine how eye-gaze contributes to reference resolution in such a setting. Specifically, we present an integrated probabilistic framework that combines speech and eye-gaze for reference resolution. We further examine the relationship between eye-gaze and increased domain modeling with corresponding linguistic processing. Our empirical results show that the incorporation of eye-gaze significantly improves reference resolution performance. This improvement is most dramatic when a simple domain model is used. Our results also show that minimal domain modeling combined with eye-gaze significantly outperforms complex domain modeling without eye-gaze, which indicates that eye-gaze can be used to potentially compensate a lack of domain modeling for reference resolution.},
added-at = {2012-05-30T10:52:32.000+0200},
author = {Prasov, Zahar and Chai, Joyce Y.},
biburl = {https://www.bibsonomy.org/bibtex/2e7a235d70d2befb868e7249df67d85ef/flint63},
booktitle = {Proceedings of IUI '08: 13th International Conference on Intelligent User Interfaces, Gran Canaria, Spain},
doi = {10.1145/1378773.1378777},
file = {ACM Digital Library:2008/PrasovChai08IUI.pdf:PDF},
groups = {public},
interhash = {f02dac85f56f46c7879a73966e2c0509},
intrahash = {e7a235d70d2befb868e7249df67d85ef},
isbn = {978-1-59593-987-6},
keywords = {v1205 acm paper ai user interface multimodal interaction language processing video analysis},
pages = {20-29},
timestamp = {2018-04-16T12:39:25.000+0200},
title = {What's in a Gaze? {The} Role of Eye-Gaze in Reference Resolution in Multimodal Conversational Interfaces},
username = {flint63},
year = 2008
}