# Every child should have parents: a taxonomy refinement algorithm based on hyperbolic term embeddings

## TL;DR

This paper presents a novel taxonomy refinement algorithm using Poincaré embeddings, significantly enhancing hierarchical taxonomy induction from text by better capturing semantic relationships than Euclidean embeddings.

## Contribution

It introduces Poincaré embeddings for taxonomy refinement, improving the accuracy of hierarchical term placement and attachment in taxonomy induction tasks.

## Key findings

- Outperforms previous state-of-the-art on SemEval-2016 Task 13
- Poincaré embeddings better capture hierarchical relationships than Euclidean embeddings
- Enhances taxonomy accuracy by relocating and attaching terms more effectively

## Abstract

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.