Paper: Learning Distributions over Logical Forms for Referring Expression Generation

ACL ID D13-1197
Title Learning Distributions over Logical Forms for Referring Expression Generation
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2013
Authors

We present a new approach to referring ex- pression generation, casting it as a density es- timation problem where the goal is to learn distributions over logical expressions identi- fying sets of objects in the world. Despite an extremely large space of possible expres- sions, we demonstrate effective learning of a globally normalized log-linear distribution. This learning is enabled by a new, multi-stage approximate inference technique that uses a pruning model to construct only the most likely logical forms. We train and evaluate the approach on a new corpus of references to sets of visual objects. Experiments show the approach is able to learn accurate models, which generate over 87% of the expressions people used. Additionally, on the previously studied special case of single object r...