The Niki and Julie Corpus: Collaborative Multimodal Dialogues between Humans, Robots, and Virtual Agents (bibtex)
by Ron Artstein, Jill Boberg, Alesia Gainer, Jonathan Gratch, Emmanuel Johnson, Anton Leuski, Gale Lucas, David Traum
Abstract:
The Niki and Julie corpus contains more than 600 dialogues between human participants and a human-controlled robot or virtual agent, engaged in a series of collaborative item-ranking tasks designed to measure influence. Some of the dialogues contain deliberate conversational errors by the robot, designed to simulate the kinds of conversational breakdown that are typical of present-day automated agents. Data collected include audio and video recordings, the results of the ranking tasks, and questionnaire responses; some of the recordings have been transcribed and annotated for verbal and nonverbal feedback. The corpus has been used to study influence and grounding in dialogue. All the dialogues are in American English.
Reference:
The Niki and Julie Corpus: Collaborative Multimodal Dialogues between Humans, Robots, and Virtual Agents (Ron Artstein, Jill Boberg, Alesia Gainer, Jonathan Gratch, Emmanuel Johnson, Anton Leuski, Gale Lucas, David Traum), In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), European Language Resources Association (ELRA), 2018.
Bibtex Entry:
@inproceedings{artstein_niki_2018,
	address = {Miyazaki, Japan},
	title = {The {Niki} and {Julie} {Corpus}: {Collaborative} {Multimodal} {Dialogues} between {Humans}, {Robots}, and {Virtual} {Agents}},
	isbn = {979-10-95546-00-9},
	url = {http://www.lrec-conf.org/proceedings/lrec2018/pdf/482.pdf},
	abstract = {The Niki and Julie corpus contains more than 600 dialogues between human participants and a human-controlled robot or virtual agent, engaged in a series of collaborative item-ranking tasks designed to measure influence. Some of the dialogues contain deliberate conversational errors by the robot, designed to simulate the kinds of conversational breakdown that are typical of present-day automated agents. Data collected include audio and video recordings, the results of the ranking tasks, and questionnaire responses; some of the recordings have been transcribed and annotated for verbal and nonverbal feedback. The corpus has been used to study influence and grounding in dialogue. All the dialogues are in American English.},
	booktitle = {Proceedings of the {Eleventh} {International} {Conference} on {Language} {Resources} and {Evaluation} ({LREC} 2018)},
	publisher = {European Language Resources Association (ELRA)},
	author = {Artstein, Ron and Boberg, Jill and Gainer, Alesia and Gratch, Jonathan and Johnson, Emmanuel and Leuski, Anton and Lucas, Gale and Traum, David},
	month = may,
	year = {2018},
	keywords = {UARC, Virtual Humans}
}
Powered by bibtexbrowser