Augmenting Abstract Meaning Representation for Human-Robot Dialogue (bibtex)
by Claire Bonial, Lucia Donatelli, Stephanie M. Lukin, Stephen Tratz, Ron Artstein, David Traum, Clare R. Voss
Abstract:
We detail refinements made to Abstract Meaning Representation (AMR) that make the representation more suitable for supporting a situated dialogue system, where a human remotely controls a robot for purposes of search and rescue and reconnaissance. We propose 36 augmented AMRs that capture speech acts, tense and aspect, and spatial information. This linguistic information is vital for representing important distinctions, for example whether the robot has moved, is moving, or will move. We evaluate two existing AMR parsers for their performance on dialogue data. We also outline a model for graph-to-graph conversion, in which output from AMR parsers is converted into our refined AMRs. The design scheme presentedhere,thoughtask-specific,isextendable for broad coverage of speech acts using AMR in future task-independent work.
Reference:
Augmenting Abstract Meaning Representation for Human-Robot Dialogue (Claire Bonial, Lucia Donatelli, Stephanie M. Lukin, Stephen Tratz, Ron Artstein, David Traum, Clare R. Voss), In Proceedings of the First International Workshop on Designing Meaning Representations (DMR), Association of Computational Linguistics, 2019.
Bibtex Entry:
@inproceedings{bonial_augmenting_2019,
	address = {Florence, Italy},
	title = {Augmenting {Abstract} {Meaning} {Representation} for {Human}-{Robot} {Dialogue}},
	url = {https://www.aclweb.org/anthology/W19-3322},
	abstract = {We detail refinements made to Abstract Meaning Representation (AMR) that make the representation more suitable for supporting a situated dialogue system, where a human remotely controls a robot for purposes of search and rescue and reconnaissance. We propose 36 augmented AMRs that capture speech acts, tense and aspect, and spatial information. This linguistic information is vital for representing important distinctions, for example whether the robot has moved, is moving, or will move. We evaluate two existing AMR parsers for their performance on dialogue data. We also outline a model for graph-to-graph conversion, in which output from AMR parsers is converted into our refined AMRs. The design scheme presentedhere,thoughtask-specific,isextendable for broad coverage of speech acts using AMR in future task-independent work.},
	booktitle = {Proceedings of the {First} {International} {Workshop} on {Designing} {Meaning} {Representations} ({DMR})},
	publisher = {Association of Computational Linguistics},
	author = {Bonial, Claire and Donatelli, Lucia and Lukin, Stephanie M. and Tratz, Stephen and Artstein, Ron and Traum, David and Voss, Clare R.},
	month = aug,
	year = {2019},
	keywords = {Virtual Humans, UARC, ARL, DoD},
	pages = {199--210}
}
Powered by bibtexbrowser