We introduce the use of Poincar\'e 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 Poincar\'e embeddings over distributional semantic representations, supporting the hypothesis that they can better capture hierarchical lexical-semantic relationships than embeddings in the Euclidean space.
Cite
@article{arxiv.1906.02002,
title = {Every child should have parents: a taxonomy refinement algorithm based on hyperbolic term embeddings},
author = {Rami Aly and Shantanu Acharya and Alexander Ossa and Arne Köhn and Chris Biemann and Alexander Panchenko},
journal= {arXiv preprint arXiv:1906.02002},
year = {2019}
}
Comments
7 pages (5 + 2 pages references), 2 Figures, 3 Tables, Accepted to the ACL 2019 conference. Will appear in its proceedings