Search Results for author: Alexis Toumi

Found 14 papers, 5 papers with code

Higher-Order DisCoCat (Peirce-Lambek-Montague semantics)

no code implementations29 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.


Category Theory for Quantum Natural Language Processing

1 code implementation13 Dec 2022 Alexis Toumi

The second chapter uses DisCopy to implement QNLP models as parameterised functors from grammar to quantum circuits.

How to make qubits speak

no code implementations2 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.

Question Answering

Functorial Language Models

no code implementations26 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.

Diagrammatic Differentiation for Quantum Machine Learning

no code implementations14 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.

BIG-bench Machine Learning Quantum Machine Learning

Grammar-aware sentence classification on quantum computers

no code implementations7 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.

Binary Classification Classification +3

Foundations for Near-Term Quantum Natural Language Processing

1 code implementation7 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.

Functorial Language Games for Question Answering

no code implementations19 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.

Question Answering

Quantum Natural Language Processing on Near-Term Quantum Computers

no code implementations8 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.

Language Modelling Quantum Machine Learning +1

DisCoPy: Monoidal Categories in Python

3 code implementations6 May 2020 Giovanni de Felice, Alexis Toumi, Bob Coecke

We introduce DisCoPy, an open source toolbox for computing with monoidal categories.

Category Theory

Incremental Monoidal Grammars

no code implementations2 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.

BIG-bench Machine Learning Language Modelling

Functorial Question Answering

1 code implementation17 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.

Question Answering Sentence

Towards Compositional Distributional Discourse Analysis

no code implementations8 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.

Natural Language Understanding Question Answering +1

Cannot find the paper you are looking for? You can Submit a new open access paper.