Improving Semantic Composition with Offset Inference
Computation and Language
2017-04-25 v1
Abstract
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.
Cite
@article{arxiv.1704.06692,
title = {Improving Semantic Composition with Offset Inference},
author = {Thomas Kober and Julie Weeds and Jeremy Reffin and David Weir},
journal= {arXiv preprint arXiv:1704.06692},
year = {2017}
}
Comments
to appear at ACL 2017 (short papers)