mlsanityData to 7 Oct 2026

Functorial Language Models

arXiv 2103.14411 ↗First posted 26 Mar 2021cs.CL math.CTcited by 1

Not on the map. Why?

Abstract (arXiv)

We introduce functorial language models: a principled way to compute probability distributions over word sequences given a monoidal functor from grammar to meaning. This yields a method for training categorical compositional distributional (DisCoCat) models on raw text data. We provide a proof-of-concept implementation in DisCoPy, the Python toolbox for monoidal categories.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 13 of its 35 references that are in the map. First posted on arXiv 26 Mar 2021.

Builds on

13 of 35 references.

References · 13

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020Foundations for Near-Term Quantum Natural Language Processingcited by 51
  3. 2020Quantum Natural Language Processing on Near-Term Quantum Computerscited by 39
  4. 2015Open System Categorical Quantum Semantics in Natural Language Processingcited by 17
  5. 2013Lambek vs. Lambek: Functorial Vector Space Semantics and String Diagrams for Lambek Calculuscited by 13
  6. 2015Sentence Entailment in Compositional Distributional Semanticscited by 9
  7. 2014Reasoning about Meaning in Natural Language with Compact Closed Categories and Frobenius Algebrascited by 7
  8. 2021Diagrammatic Differentiation for Quantum Machine Learningcited by 5
  9. 2018Towards Compositional Distributional Discourse Analysiscited by 4
  10. 2019Functorial Question Answeringcited by 4
  11. 2014Autonomization of Monoidal Categoriescited by 3
  12. 2018Exploring Semantic Incrementality with Dynamic Syntax and Vector Space Semanticscited by 2
1 more
  1. 2020Incremental Monoidal Grammarscited by 2

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024Model Editing as a Robust and Denoised variant of DPO: A Case Study on Toxicitycited by 33