TY - GEN
T1 - Confidence driven unsupervised semantic parsing
AU - Goldwasser, Dan
AU - Reichart, Roi
AU - Clarke, James
AU - Roth, Dan
N1 - Funding Information:
Thanks to NICT for their support, Takayuki Kuribayashi for providing native judgments, and Marcus Dickinson for comments on an early draft.
PY - 2011
Y1 - 2011
N2 - Current approaches for semantic parsing take a supervised approach requiring a considerable amount of training data which is expensive and difficult to obtain. This supervision bottleneck is one of the major difficulties in scaling up semantic parsing. We argue that a semantic parser can be trained effectively without annotated data, and introduce an unsupervised learning algorithm. The algorithm takes a self training approach driven by confidence estimation. Evaluated over Geoquery, a standard dataset for this task, our system achieved 66% accuracy, compared to 80% of its fully supervised counterpart, demonstrating the promise of unsupervised approaches for this task.
AB - Current approaches for semantic parsing take a supervised approach requiring a considerable amount of training data which is expensive and difficult to obtain. This supervision bottleneck is one of the major difficulties in scaling up semantic parsing. We argue that a semantic parser can be trained effectively without annotated data, and introduce an unsupervised learning algorithm. The algorithm takes a self training approach driven by confidence estimation. Evaluated over Geoquery, a standard dataset for this task, our system achieved 66% accuracy, compared to 80% of its fully supervised counterpart, demonstrating the promise of unsupervised approaches for this task.
UR - http://www.scopus.com/inward/record.url?scp=84859018994&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84859018994&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84859018994
SN - 9781932432879
T3 - ACL-HLT 2011 - Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies
SP - 1486
EP - 1495
BT - ACL-HLT 2011 - Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics
T2 - 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, ACL-HLT 2011
Y2 - 19 June 2011 through 24 June 2011
ER -