CLLGSep 15, 2021

Comparing Euclidean and Hyperbolic Embeddings on the WordNet Nouns Hypernymy Graph

arXiv:2109.07488v1662 citations
Originality Synthesis-oriented
AI Analysis

This work provides an updated comparison for researchers in natural language processing and graph embedding, though it is incremental as it revisits and refines existing findings.

The paper tackled the problem of comparing Euclidean and hyperbolic embeddings for the WordNet nouns hypernymy graph, finding that Euclidean embeddings perform at least as well as hyperbolic ones when using at least 50 dimensions, contrary to prior claims.

Nickel and Kiela (2017) present a new method for embedding tree nodes in the Poincare ball, and suggest that these hyperbolic embeddings are far more effective than Euclidean embeddings at embedding nodes in large, hierarchically structured graphs like the WordNet nouns hypernymy tree. This is especially true in low dimensions (Nickel and Kiela, 2017, Table 1). In this work, we seek to reproduce their experiments on embedding and reconstructing the WordNet nouns hypernymy graph. Counter to what they report, we find that Euclidean embeddings are able to represent this tree at least as well as Poincare embeddings, when allowed at least 50 dimensions. We note that this does not diminish the significance of their work given the impressive performance of hyperbolic embeddings in very low-dimensional settings. However, given the wide influence of their work, our aim here is to present an updated and more accurate comparison between the Euclidean and hyperbolic embeddings.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes