Foundations for near-term quantum natural language processing

B Coecke, G de Felice, K Meichanetzidis… - arxiv preprint arxiv …, 2020 - arxiv.org
We provide conceptual and mathematical foundations for near-term quantum natural
language processing (QNLP), and do so in quantum computer scientist friendly terms. We …

DisCoPy: Monoidal categories in python

G de Felice, A Toumi, B Coecke - arxiv preprint arxiv:2005.02975, 2020 - arxiv.org
We introduce DisCoPy, an open source toolbox for computing with monoidal categories. The
library provides an intuitive syntax for defining string diagrams and monoidal functors. Its …

Towards compositional interpretability for xai

S Tull, R Lorenz, S Clark, I Khan, B Coecke - arxiv preprint arxiv …, 2024 - arxiv.org
Artificial intelligence (AI) is currently based largely on black-box machine learning models
which lack interpretability. The field of eXplainable AI (XAI) strives to address this major …

Distilling text into circuits

V Wang-Mascianica, J Liu, B Coecke - arxiv preprint arxiv:2301.10595, 2023 - arxiv.org
This paper concerns the structure of meanings within natural language. Earlier, a framework
named DisCoCirc was sketched that (1) is compositional and distributional (aka …

[HTML][HTML] A compositional model of consciousness based on consciousness-only

CM Signorelli, Q Wang, I Khan - Entropy, 2021 - mdpi.com
Scientific studies of consciousness rely on objects whose existence is assumed to be
independent of any consciousness. On the contrary, we assume consciousness to be …

Category theory for quantum natural language processing

A Toumi - arxiv preprint arxiv:2212.06615, 2022 - arxiv.org
This thesis introduces quantum natural language processing (QNLP) models based on a
simple yet powerful analogy between computational linguistics and quantum mechanics …

Compositionality as we see it, everywhere around us

B Coecke - The Quantum-Like Revolution: A Festschrift for Andrei …, 2023 - Springer
There are different meanings of the term “compositionality” within science: what one
researcher would call compositional, is not at all compositional for another researcher. The …

From conceptual spaces to quantum concepts: formalising and learning structured conceptual models

S Tull, RA Shaikh, SS Zemljič, S Clark - Quantum Machine Intelligence, 2024 - Springer
In this article we present a new modelling framework for structured concepts using a
category-theoretic generalisation of conceptual spaces, and show how the conceptual …

Meaning updating of density matrices

B Coecke, K Meichanetzidis - arxiv preprint arxiv:2001.00862, 2020 - arxiv.org
The DisCoCat model of natural language meaning assigns meaning to a sentence given:(i)
the meanings of its words, and,(ii) its grammatical structure. The recently introduced …

Breaking free transformer models: task-specific context attribution promises improved generalizability without fine-tuning pre-trained LLMs

S Tytarenko, MR Amin - arxiv preprint arxiv:2401.16638, 2024 - arxiv.org
Fine-tuning large pre-trained language models (LLMs) on particular datasets is a commonly
employed strategy in Natural Language Processing (NLP) classification tasks. However, this …