Improving Semantic Composition with Offset Inference
Thomas Kober, Julie Weeds, Jeremy Reffin, David James Weir · 2017
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.