Improving Semantic Composition with Offset Inference

04/21/2017

∙

by   Thomas Kober, et al.

∙

University of Sussex

∙

0

∙

share

Count-based distributional semantic models suffer from sparsity due to unobserved but plausible co-occurrences in any text collection. This problem is amplified for models like Anchored Packed Trees (APTs), that take the grammatical type of a co-occurrence into account. We therefore introduce a novel form of distributional inference that exploits the rich type structure in APTs and infers missing data by the same mechanism that is used for semantic composition.