Paper: Reducing Grounded Learning Tasks To Grammatical Inference

ACL ID D11-1131
Title Reducing Grounded Learning Tasks To Grammatical Inference
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2011
Authors

It is often assumed that ‘grounded’ learning tasks are beyond the scope of grammaticalin- ference techniques. In this paper, we show that the grounded task of learning a seman- tic parserfromambiguoustrainingdata as dis- cussed in Kim and Mooney (2010) can be re- duced to a ProbabilisticContext-Free Gram- mar learning task in a way that gives state of the art results. We further show that ad- ditionally letting our model learn the lan- guage’s canonical word order improves its performanceand leads to the highest seman- tic parsing f-scores previously reportedin the literature.1