# Unsupervised Word Polysemy Quantification with Multiresolution Grids of Contextual Embeddings

arXiv: https://arxiv.org/abs/2003.10224 · HTML: https://mlsanity.com/paper/2003.10224/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Mar 2020.

## Built on by (most cited first, 5 of 5)

- [Putting Words in BERT's Mouth: Navigating Contextualized Vector Spaces with Pseudowords](https://mlsanity.com/paper/2109.11491/) (2021)
- [In the LLM era, Word Sense Induction remains unsolved](https://mlsanity.com/paper/2603.11686/) (2026)
- [NLP Research and Resources at DaSciM, Ecole Polytechnique](https://mlsanity.com/paper/2112.00566/) (2021)
- [Word Sense Induction with Hierarchical Clustering and Mutual Information Maximization](https://mlsanity.com/paper/2210.05422/) (2022)
- [Accurate and Efficient Statistical Testing for Word Semantic Breadth](https://mlsanity.com/paper/2605.08048/) (2026)

## Abstract (arXiv)

The number of senses of a given word, or polysemy, is a very subjective notion, which varies widely across annotators and resources. We propose a novel method to estimate polysemy, based on simple geometry in the contextual embedding space. Our approach is fully unsupervised and purely data-driven. We show through rigorous experiments that our rankings are well correlated (with strong statistical significance) with 6 different rankings derived from famous human-constructed resources such as WordNet, OntoNotes, Oxford, Wikipedia etc., for 6 different standard metrics. We also visualize and analyze the correlation between the human rankings. A valuable by-product of our method is the ability to sample, at no extra cost, sentences containing different senses of a given word. Finally, the fully unsupervised nature of our method makes it applicable to any language. Code and data are publicly available at https://github.com/ksipos/polysemy-assessment . The paper was accepted as a long paper at EACL 2021.