acl2017
Code and resources of the ACL 2017 paper "Improving Semantic Composition with Offset Inference"
view repo
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.
READ FULL TEXTCode and resources of the ACL 2017 paper "Improving Semantic Composition with Offset Inference"