no code implementations • 29 Nov 2023 • Alexis Toumi, Giovanni De Felice
We propose a new definition of higher-order DisCoCat (categorical compositional distributional) models where the meaning of a word is not a diagram, but a diagram-valued higher-order function.
1 code implementation • 13 Dec 2022 • Alexis Toumi
The second chapter uses DisCopy to implement QNLP models as parameterised functors from grammar to quantum circuits.
1 code implementation • 8 Oct 2021 • Dimitri Kartsaklis, Ian Fan, Richie Yeung, Anna Pearson, Robin Lorenz, Alexis Toumi, Giovanni De Felice, Konstantinos Meichanetzidis, Stephen Clark, Bob Coecke
We present lambeq, the first high-level Python library for Quantum Natural Language Processing (QNLP).
no code implementations • 2 Jul 2021 • Bob Coecke, Giovanni De Felice, Konstantinos Meichanetzidis, Alexis Toumi
This is a story about making quantum computers speak, and doing so in a quantum-native, compositional and meaning-aware manner.
no code implementations • 26 Mar 2021 • Alexis Toumi, Alex Koziell-Pipe
We introduce functorial language models: a principled way to compute probability distributions over word sequences given a monoidal functor from grammar to meaning.
no code implementations • 14 Mar 2021 • Alexis Toumi, Richie Yeung, Giovanni De Felice
We introduce diagrammatic differentiation for tensor calculus by generalising the dual number construction from rigs to monoidal categories.
no code implementations • 7 Dec 2020 • Konstantinos Meichanetzidis, Alexis Toumi, Giovanni De Felice, Bob Coecke
In this work, we focus on the capabilities of noisy intermediate-scale quantum (NISQ) hardware and perform the first implementation of an NLP task on a NISQ processor, using the DisCoCat framework.
1 code implementation • 7 Dec 2020 • Bob Coecke, Giovanni De Felice, Konstantinos Meichanetzidis, Alexis Toumi
We recall how the quantum model for natural language that we employ canonically combines linguistic meanings with rich linguistic structure, most notably grammar.
no code implementations • 19 May 2020 • Giovanni de Felice, Elena Di Lavore, Mario Román, Alexis Toumi
We present some categorical investigations into Wittgenstein's language-games, with applications to game-theoretic pragmatics and question-answering in natural language processing.
no code implementations • 8 May 2020 • Konstantinos Meichanetzidis, Stefano Gogioso, Giovanni de Felice, Nicolò Chiappori, Alexis Toumi, Bob Coecke
In this work, we describe a full-stack pipeline for natural language processing on near-term quantum computers, aka QNLP.
3 code implementations • 6 May 2020 • Giovanni de Felice, Alexis Toumi, Bob Coecke
We introduce DisCoPy, an open source toolbox for computing with monoidal categories.
Category Theory
no code implementations • 2 Jan 2020 • Dan Shiebler, Alexis Toumi, Mehrnoosh Sadrzadeh
In this work we define formal grammars in terms of free monoidal categories, along with a functor from the category of formal grammars to the category of automata.
1 code implementation • 17 May 2019 • Giovanni de Felice, Konstantinos Meichanetzidis, Alexis Toumi
Distributional compositional (DisCo) models are functors that compute the meaning of a sentence from the meaning of its words.
no code implementations • 8 Nov 2018 • Bob Coecke, Giovanni De Felice, Dan Marsden, Alexis Toumi
Categorical compositional distributional semantics provide a method to derive the meaning of a sentence from the meaning of its individual words: the grammatical reduction of a sentence automatically induces a linear map for composing the word vectors obtained from distributional semantics.