mlsanityData to 14 Oct 2026

Composing Conversational Negation

arXiv 2107.06820 ↗First posted 14 Jul 2021cs.CL math.CTcited by 7

Not on the map. Why?

Abstract (arXiv)

Negation in natural language does not follow Boolean logic and is therefore inherently difficult to model. In particular, it takes into account the broader understanding of what is being negated. In previous work, we proposed a framework for the negation of words that accounts for 'worldly context'. This paper extends that proposal now accounting for the compositional structure inherent in language within the DisCoCirc framework. We compose the negations of single words to capture the negation of sentences. We also describe how to model the negation of words whose meanings evolve in the text.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 13 of its 36 references that are in the map. First posted on arXiv 14 Jul 2021.

Builds on

13 of 36 references.

References · 13

  1. 2019The Mathematics of Text Structurecited by 24
  2. 2015Open System Categorical Quantum Semantics in Natural Language Processingcited by 17
  3. 2017Interacting Conceptual Spaces I : Grammatical Composition of Conceptscited by 13
  4. 2020Modelling Lexical Ambiguity with Density Matricescited by 11
  5. 2015Sentence Entailment in Compositional Distributional Semanticscited by 9
  6. 2020Meaning updating of density matricescited by 9
  7. 2020Towards logical negation for compositional distributional semanticscited by 9
  8. 2021Conversational Negation using Worldly Context in Compositional Distributional Semanticscited by 9
  9. 2013Computing Lexical Contrastcited by 7
  10. 2020Cats climb entails mammals move: preserving hyponymy in compositional distributional semanticscited by 6
  11. 2015Distributional Sentence Entailment Using Density Matricescited by 4
  12. 2016Distributional Inclusion Hypothesis for Tensor-based Compositioncited by 4
1 more
  1. 2015A Compositional Explanation of the Pet Fish Phenomenoncited by 3

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 5; 2024: 1.

7 papers.

  1. 2023Distilling Text into Circuitscited by 7
  2. 2023On Meta-Promptingcited by 6
  3. 2022Language-independence of DisCoCirc's Text Circuits: English and Urducited by 5
  4. 2023A Pipeline For Discourse Circuits From CCGcited by 3
  5. 2023From Conceptual Spaces to Quantum Concepts: Formalising and Learning Structured Conceptual Modelscited by 3
  6. 2023Formalising and Learning a Quantum Model of Conceptscited by 0
  7. 2024Density Matrices for Metaphor Understandingcited by 0