Dialogue Structure Parsing on Multi-Floor Dialogue Based on Multi-Task Learning (bibtex)
by Kawano, Seiya, Yoshino, Koichiro, Traum, David and Nakamura, Satoshi
Abstract:
A multi-floor dialogue consists of multiple sets of dialogue participants, each conversing within their own floor, but also at least one multicommunicating member who is a participant of multiple floors and coordinating each to achieve a shared dialogue goal. The structure of such dialogues can be complex, involving intentional structure and relations that are within or across floors. In this study, we propose a neural dialogue structure parser based on multi-task learning and an attention mechanism on multi-floor dialogues in a collaborative robot navigation domain. Our experimental results show that our proposed model improved the dialogue structure parsing performance more than those of single models, which are trained on each dialogue structure parsing task in multi-floor dialogues.
Reference:
Dialogue Structure Parsing on Multi-Floor Dialogue Based on Multi-Task Learning (Kawano, Seiya, Yoshino, Koichiro, Traum, David and Nakamura, Satoshi), In 1st RobotDial Workshop on Dialogue Models for Human-Robot Interaction, ISCA, 2021.
Bibtex Entry:
@inproceedings{kawano_dialogue_2021,
	title = {Dialogue {Structure} {Parsing} on {Multi}-{Floor} {Dialogue} {Based} on {Multi}-{Task} {Learning}},
	url = {http://www.isca-speech.org/archive/RobotDial_2021/abstracts/4.html},
	doi = {10.21437/RobotDial.2021-4},
	abstract = {A multi-floor dialogue consists of multiple sets of dialogue participants, each conversing within their own floor, but also at least one multicommunicating member who is a participant of multiple floors and coordinating each to achieve a shared dialogue goal. The structure of such dialogues can be complex, involving intentional structure and relations that are within or across floors. In this study, we propose a neural dialogue structure parser based on multi-task learning and an attention mechanism on multi-floor dialogues in a collaborative robot navigation domain. Our experimental results show that our proposed model improved the dialogue structure parsing performance more than those of single models, which are trained on each dialogue structure parsing task in multi-floor dialogues.},
	language = {en},
	urldate = {2021-04-15},
	booktitle = {1st {RobotDial} {Workshop} on {Dialogue} {Models} for {Human}-{Robot} {Interaction}},
	publisher = {ISCA},
	author = {Kawano, Seiya and Yoshino, Koichiro and Traum, David and Nakamura, Satoshi},
	month = jan,
	year = {2021},
	keywords = {Virtual Humans, ARL, Dialogue, Natural Language},
	pages = {21--29},
	file = {Kawano et al. - 2021 - Dialogue Structure Parsing on Multi-Floor Dialogue.pdf:files/1749/Kawano et al. - 2021 - Dialogue Structure Parsing on Multi-Floor Dialogue.pdf:application/pdf},
}
Powered by bibtexbrowser