# More than just Frequency? Demasking Unsupervised Hypernymy Prediction Methods

arXiv: https://arxiv.org/abs/2106.00055 · HTML: https://mlsanity.com/paper/2106.00055/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 34 references that are in the map.
- First posted on arXiv 31 May 2021.

## Builds on (most cited first, 2 of 2)

- [Improving Hypernymy Detection with an Integrated Path-based and Distributional Method](https://mlsanity.com/paper/1603.06076/) (2016)
- [Hypernyms under Siege: Linguistically-motivated Artillery for Hypernymy Detection](https://mlsanity.com/paper/1612.04460/) (2016)

## Built on by (most cited first, 2 of 2)

- [Norm of Word Embedding Encodes Information Gain](https://mlsanity.com/paper/2212.09663/) (2022)
- [Neural Machine Translation Data Generation and Augmentation using ChatGPT](https://mlsanity.com/paper/2307.05779/) (2023)

## Abstract (arXiv)

This paper presents a comparison of unsupervised methods of hypernymy prediction (i.e., to predict which word in a pair of words such as fish-cod is the hypernym and which the hyponym). Most importantly, we demonstrate across datasets for English and for German that the predictions of three methods (WeedsPrec, invCL, SLQS Row) strongly overlap and are highly correlated with frequency-based predictions. In contrast, the second-order method SLQS shows an overall lower accuracy but makes correct predictions where the others go wrong. Our study once more confirms the general need to check the frequency bias of a computational method in order to identify frequency-(un)related effects.