Can I read Every Child Should Have Parents: a Taxonomy Refinement Algorithm Based on Hyperbolic Term Embeddings on EtoBox?

Every Child Should Have Parents: a Taxonomy Refinement Algorithm Based on Hyperbolic Term Embeddings by Aly, Rami; Acharya, Shantanu; Ossa, Alexander; Köhn, Arne; Biemann, Chris; Panchenko, Alexander is a scholarly article available to read on EtoBox.

What is Every Child Should Have Parents: a Taxonomy Refinement Algorithm Based on Hyperbolic Term Embeddings about?

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.

Author

Aly, Rami; Acharya, Shantanu; Ossa, Alexander; Köhn, Arne; Biemann, Chris; Panchenko, Alexander

Published

2019

Language

EN