Real-Time Understanding of Complex Discriminative Scene Descriptions (bibtex)
by Ramesh Manuvinakurike, Casey Kennington, David DeVault, David Schlangen
Abstract:
Real-world scenes typically have complex structure, and utterances about them consequently do as well. We devise and evaluate a model that processes descriptions of complex configurations of geometric shapes and can identify the described scenes among a set of candidates, including similar distractors. The model works with raw images of scenes, and by design can work word-by-word incrementally. Hence, it can be used in highly-responsive interactive and situated settings. Using a corpus of descriptions from game-play between human subjects (who found this to be a challenging task), we show that reconstruction of description structure in our system contributes to task success and supports the performance of the word-based model of grounded semantics that we use.
Reference:
Real-Time Understanding of Complex Discriminative Scene Descriptions (Ramesh Manuvinakurike, Casey Kennington, David DeVault, David Schlangen), In Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue, Association for Computational Linguistics, 2016.
Bibtex Entry:
@inproceedings{manuvinakurike_real-time_2016,
	address = {Los Angeles, CA},
	title = {Real-{Time} {Understanding} of {Complex} {Discriminative} {Scene} {Descriptions}},
	url = {http://www.aclweb.org/anthology/W16-3630},
	abstract = {Real-world scenes typically have complex structure, and utterances about them consequently do as well. We devise and evaluate a model that processes descriptions of complex configurations of geometric shapes and can identify the described scenes among a set of candidates, including similar distractors. The model works with raw images of scenes, and by design can work word-by-word incrementally. Hence, it can be used in highly-responsive interactive and situated settings. Using a corpus of descriptions from game-play between human subjects (who found this to be a challenging task), we show that reconstruction of description structure in our system contributes to task success and supports the performance of the word-based model of grounded semantics that we use.},
	booktitle = {Proceedings of the 17th {Annual} {Meeting} of the {Special} {Interest} {Group} on {Discourse} and {Dialogue}},
	publisher = {Association for Computational Linguistics},
	author = {Manuvinakurike, Ramesh and Kennington, Casey and DeVault, David and Schlangen, David},
	month = sep,
	year = {2016},
	keywords = {UARC, Virtual Humans},
	pages = {232--241}
}
Powered by bibtexbrowser