Every child should have parents: a taxonomy refinement algorithm
based on hyperbolic term embeddings
Abstract
We introduce the use of Poincare embeddings ´
to improve existing state-of-the-art approaches
to domain-specific taxonomy induction from
text as a signal for both relocating wrong hyponym terms within a (pre-induced) taxonomy
as well as for attaching disconnected terms
in a taxonomy. This method substantially
improves previous state-of-the-art results on
the SemEval-2016 Task 13 on taxonomy extraction. We demonstrate the superiority of
Poincare embeddings over distributional se- ´
mantic representations, supporting the hypothesis that they can better capture hierarchical lexical-semantic relationships than embeddings in the Euclidean space.