Learning and Reusing Dialog for Repeated Interactions with a Situated Social Agent (bibtex)
by James Kennedy, Iolanda Leite, André Pereira, Ming Sun, Boyang Li, Rishub Jain, Ricson Cheng, Eli Pincus, Elizabeth J. Carter, Jill Fain Lehman
Abstract:
Content authoring for conversations is a limiting factor in creating verbal interactions with intelligent virtual agents. Building on techniques utilizing semi-situated learning in an incremental crowdworking pipeline, this paper introduces an embodied agent that self-authors its own dialog for social chat. In particular, the autonomous use of crowdworkers is supplemented with a generalization method that borrows and assesses the validity of dialog across conversational states. We argue that the approach offers a community-focused tailoring of dialog responses that is not available in approaches that rely solely on statistical methods across big data. We demonstrate the advantages that this can bring to interactions through data collected from 486 conversations between a situated social agent and 22 users during a 3 week long evaluation period.
Reference:
Learning and Reusing Dialog for Repeated Interactions with a Situated Social Agent (James Kennedy, Iolanda Leite, André Pereira, Ming Sun, Boyang Li, Rishub Jain, Ricson Cheng, Eli Pincus, Elizabeth J. Carter, Jill Fain Lehman), In Proceedings of the International Conference on Intelligent Virtual Agents, Springer International Publishing, volume 10498, 2017. (DOI: 10.1007/978-3-319-67401-8\_22)
Bibtex Entry:
@inproceedings{kennedy_learning_2017,
	address = {Stockholm, Sweden},
	title = {Learning and {Reusing} {Dialog} for {Repeated} {Interactions} with a {Situated} {Social} {Agent}},
	volume = {10498},
	isbn = {978-3-319-67400-1 978-3-319-67401-8},
	url = {http://link.springer.com/10.1007/978-3-319-67401-8_22},
	abstract = {Content authoring for conversations is a limiting factor in creating verbal interactions with intelligent virtual agents. Building on techniques utilizing semi-situated learning in an incremental crowdworking pipeline, this paper introduces an embodied agent that self-authors its own dialog for social chat. In particular, the autonomous use of crowdworkers is supplemented with a generalization method that borrows and assesses the validity of dialog across conversational states. We argue that the approach offers a community-focused tailoring of dialog responses that is not available in approaches that rely solely on statistical methods across big data. We demonstrate the advantages that this can bring to interactions through data collected from 486 conversations between a situated social agent and 22 users during a 3 week long evaluation period.},
	booktitle = {Proceedings of the {International} {Conference} on {Intelligent} {Virtual} {Agents}},
	publisher = {Springer International Publishing},
	author = {Kennedy, James and Leite, Iolanda and Pereira, André and Sun, Ming and Li, Boyang and Jain, Rishub and Cheng, Ricson and Pincus, Eli and Carter, Elizabeth J. and Lehman, Jill Fain},
	month = aug,
	year = {2017},
	note = {DOI: 10.1007/978-3-319-67401-8\_22},
	keywords = {Virtual Humans},
	pages = {192--204}
}
Powered by bibtexbrowser