# Modelling Lexical Ambiguity with Density Matrices

arXiv: https://arxiv.org/abs/2010.05670 · HTML: https://mlsanity.com/paper/2010.05670/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Oct 2020.

## Built on by (most cited first, 11 of 11)

- [Word2Box: Capturing Set-Theoretic Semantics of Words using Box Embeddings](https://mlsanity.com/paper/2106.14361/) (2021)
- [Composing Conversational Negation](https://mlsanity.com/paper/2107.06820/) (2021)
- [Distilling Text into Circuits](https://mlsanity.com/paper/2301.10595/) (2023)
- [How to make qubits speak](https://mlsanity.com/paper/2107.06776/) (2021)
- [Should Semantic Vector Composition be Explicit? Can it be Linear?](https://mlsanity.com/paper/2104.06555/) (2021)
- [Grover's Algorithm for Question Answering](https://mlsanity.com/paper/2106.05299/) (2021)
- [Sentence Ambiguity, Grammaticality and Complexity Probes](https://mlsanity.com/paper/2210.06928/) (2022)
- [Traitement quantique des langues : 'etat de l'art](https://mlsanity.com/paper/2406.15370/) (2024)
- [Density Matrices for Metaphor Understanding](https://mlsanity.com/paper/2408.11846/) (2024)
- [Quantum Methods for Managing Ambiguity in Natural Language Processing](https://mlsanity.com/paper/2504.00040/) (2025)
- [As Easy as Rocket Science: Assessing the Ability of Large Language Models to Interpret Negation in Figurative Language](https://mlsanity.com/paper/2606.18922/) (2026)

## Abstract (arXiv)

Words can have multiple senses. Compositional distributional models of meaning have been argued to deal well with finer shades of meaning variation known as polysemy, but are not so well equipped to handle word senses that are etymologically unrelated, or homonymy. Moving from vectors to density matrices allows us to encode a probability distribution over different senses of a word, and can also be accommodated within a compositional distributional model of meaning. In this paper we present three new neural models for learning density matrices from a corpus, and test their ability to discriminate between word senses on a range of compositional datasets. When paired with a particular composition method, our best model outperforms existing vector-based compositional models as well as strong sentence encoders.