mlsanityData to 14 Oct 2026

Density Matrices for Metaphor Understanding

arXiv 2408.11846 ↗First posted 12 Aug 2024cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

In physics, density matrices are used to represent mixed states, i.e. probabilistic mixtures of pure states. This concept has previously been used to model lexical ambiguity. In this paper, we consider metaphor as a type of lexical ambiguity, and examine whether metaphorical meaning can be effectively modelled using mixtures of word senses. We find that modelling metaphor is significantly more difficult than other kinds of lexical ambiguity, but that our best-performing density matrix method outperforms simple baselines as well as some neural language models.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 39 references that are in the map. First posted on arXiv 12 Aug 2024.

Builds on

18 of 39 references.

References · 18

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  4. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
  5. 2017Supervised Learning of Universal Sentence Representations from Natural Language Inference Datacited by 432
  6. 2021QNLP in Practice: Running Compositional Models of Meaning on a Quantum Computercited by 67
  7. 2019The Mathematics of Text Structurecited by 24
  8. 2015Open System Categorical Quantum Semantics in Natural Language Processingcited by 17
  9. 2020Modelling Lexical Ambiguity with Density Matricescited by 11
  10. 2015Sentence Entailment in Compositional Distributional Semanticscited by 9
  11. 2020Meaning updating of density matricescited by 9
  12. 2020Towards logical negation for compositional distributional semanticscited by 9
6 more
  1. 2021Conversational Negation using Worldly Context in Compositional Distributional Semanticscited by 9
  2. 2021Composing Conversational Negationcited by 7
  3. 2020Cats climb entails mammals move: preserving hyponymy in compositional distributional semanticscited by 6
  4. 2020Language Modeling with Reduced Densitiescited by 5
  5. 2015Compositional Distributional Semantics with Compact Closed Categories and Frobenius Algebrascited by 4
  6. 2015Distributional Sentence Entailment Using Density Matricescited by 4

Built on by

Not cited yet.