Paper ID: 2211.04462

Hyperbolic Centroid Calculations for Text Classification

Aydın Gerek, Cüneyt Ferahlar, Bilge Şipal Sert, Mehmet Can Yüney, Onur Taşdemir, Zeynep Billur Kalafat, Mert Kelkit, Murat Can Ganiz

A new development in NLP is the construction of hyperbolic word embeddings. As opposed to their Euclidean counterparts, hyperbolic embeddings are represented not by vectors, but by points in hyperbolic space. This makes the most common basic scheme for constructing document representations, namely the averaging of word vectors, meaningless in the hyperbolic setting. We reinterpret the vector mean as the centroid of the points represented by the vectors, and investigate various hyperbolic centroid schemes and their effectiveness at text classification.

Submitted: Nov 8, 2022