Publications (52)
Formalising Concepts as Grounded Abstractions
Stephen Clark, Alexander Lerchner, Tamara von Glehn +4
The notion of concept has been studied for centuries, by philosophers, linguists, cognitive scientists, and researchers in artificial intelligence (Margolis & Laurence, 1999). Ther…
Learning to Personalize for Web Search Sessions
Saad Aloteibi, Stephen Clark
The task of session search focuses on using interaction data to improve relevance for the user's next query at the session level. In this paper, we formulate session search as a pe…
Virtual Embodiment: A Scalable Long-Term Strategy for Artificial Intelligence Research
Douwe Kiela, Luana Bulat, Anita L. Vero +1
Meaning has been called the "holy grail" of a variety of scientific disciplines, ranging from linguistics to philosophy, psychology and the neurosciences. The field of Artifical In…
Neural Generative Rhetorical Structure Parsing
Amandla Mabona, Laura Rimell, Stephen Clark +1
Rhetorical structure trees have been shown to be useful for several document-level tasks including summarization and document classification. Previous approaches to RST parsing hav…
Jointly Learning Sentence Embeddings and Syntax with Unsupervised Tree-LSTMs
Jean Maillard, Stephen Clark, Dani Yogatama
We introduce a neural network that represents sentences by composing their words according to induced binary parse trees. We use Tree-LSTM as our composition function, applied alon…
Concrete Sentence Spaces for Compositional Distributional Models of Meaning
Edward Grefenstette, Mehrnoosh Sadrzadeh, Stephen Clark +2
Coecke, Sadrzadeh, and Clark (arXiv:1003.4394v1 [cs.CL]) developed a compositional model of meaning for distributional semantics, in which each word in a sentence has a meaning vec…
Interactions of Q-balls and matter
Stephen Clark
We know from previous work \cite{clark} that non topological solitons, Q balls, evaporate into fermions. All the constructions we used to find evaporation rate were dased on the fa…
Borg-Marchenko-type Uniqueness Results for CMV Operators
Stephen Clark, Fritz Gesztesy, Maxim Zinchenko
We prove local and global versions of Borg-Marchenko-type uniqueness theorems for half-lattice and full-lattice CMV operators (CMV for Cantero, Moral, and Velazquez \cite{CMV03}).…
A quantum teleportation inspired algorithm produces sentence meaning from word meaning and grammatical structure
Stephen Clark, Bob Coecke, Edward Grefenstette +2
We discuss an algorithm which produces the meaning of a sentence given meanings of its words, and its resemblance to quantum teleportation. In fact, this protocol was the main sour…
Towards Compositional Interpretability for XAI
Sean Tull, Robin Lorenz, Stephen Clark +2
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…
Understanding Early Word Learning in Situated Artificial Agents
Felix Hill, Stephen Clark, Karl Moritz Hermann +1
Neural network-based systems can now learn to locate the referents of words and phrases in images, answer questions about visual scenes, and execute symbolic instructions as first-…
Stability radius and internal versus external stability in Banach spaces: an evolution semigroup approach
Stephen Clark, Yuri Latushkin, Stephen J. Montgomery-Smith +1
In this paper the theory of evolution semigroups is developed and used to provide a framework to study the stability of general linear control systems. These include time-varying s…
Probing Emergent Semantics in Predictive Agents via Question Answering
Abhishek Das, Federico Carnevale, Hamza Merzic +8
Recent work has shown how predictive modeling can endow agents with rich knowledge of their surroundings, improving their ability to act in complex environments. We propose questio…
Peptide Binding Classification on Quantum Computers
Charles London, Douglas Brown, Wenduan Xu +5
We conduct an extensive study on using near-term quantum computers for a task in the domain of computational biology. By constructing quantum models based on parameterised quantum…
Coupling of effective one-dimensional two-level atoms to squeezed light
Stephen Clark, Scott Parkins
A cavity QED system is analyzed which duplicates the dynamics of a two-level atom in free space interacting exclusively with broadband squeezed light. We consider atoms in a three…
Imitating Interactive Intelligence
Josh Abramson, Arun Ahuja, Iain Barr +26
A common vision from science fiction is that robots will one day inhabit our physical spaces, sense the world as we do, assist our physical labours, and communicate with us through…
Scalable Syntax-Aware Language Models Using Knowledge Distillation
Adhiguna Kuncoro, Chris Dyer, Laura Rimell +2
Prior work has shown that, on small amounts of training data, syntactic neural language models learn structurally sensitive generalisations more successfully than sequential langua…
Something Old, Something New: Grammar-based CCG Parsing with Transformer Models
Stephen Clark
This report describes the parsing problem for Combinatory Categorial Grammar (CCG), showing how a combination of Transformer-based neural models and a symbolic CCG grammar can lead…
Using Sentence Plausibility to Learn the Semantics of Transitive Verbs
Tamara Polajnar, Laura Rimell, Stephen Clark
The functional approach to compositional distributional semantics considers transitive verbs to be linear maps that transform the distributional vectors representing nouns into a v…
lambeq: An Efficient High-Level Python Library for Quantum NLP
Dimitri Kartsaklis, Ian Fan, Richie Yeung +7
We present lambeq, the first high-level Python library for Quantum Natural Language Processing (QNLP). The open-source toolkit offers a detailed hierarchy of modules and classes im…
The Frobenius anatomy of word meanings I: subject and object relative pronouns
Mehrnoosh Sadrzadeh, Stephen Clark, Bob Coecke
This paper develops a compositional vector-based semantics of subject and object relative pronouns within a categorical framework. Frobenius algebras are used to formalise the oper…
Boundary Data Maps and Krein's Resolvent Formula for Sturm-Liouville Operators on a Finite Interval
Stephen Clark, Fritz Gesztesy, Roger Nichols +1
We continue the study of boundary data maps, that is, generalizations of spectral parameter dependent Dirichlet-to-Neumann maps for (three-coefficient) Sturm-Liouville operators on…
Q-Ball Condensation
Stephen Clark
Q-balls arise in particle theories with U(1) global symmetry. The coupling of the corresponding scalar field to fermions leads to Q-ball evaporation. In this paper we consider the…
Learning to Segment Actions from Observation and Narration
Daniel Fried, Jean-Baptiste Alayrac, Phil Blunsom +3
We apply a generative segmental model of task structure, guided by narration, to action segmentation in video. We focus on unsupervised and weakly-supervised settings where no acti…
Environmental drivers of systematicity and generalization in a situated agent
Felix Hill, Andrew Lampinen, Rosalia Schneider +4
The question of whether deep neural networks are good at generalising beyond their immediate training experience is of critical importance for learning-based approaches to AI. Here…
Enhancing Surgical Performance in Cardiothoracic Surgery with Innovations from Computer Vision and Artificial Intelligence: A Narrative Review
Merryn D. Constable, Hubert P. H. Shum, Stephen Clark
When technical requirements are high, and patient outcomes are critical, opportunities for monitoring and improving surgical skills via objective motion analysis feedback may be pa…
Emergent Communication through Negotiation
Kris Cao, Angeliki Lazaridou, Marc Lanctot +3
Multi-agent reinforcement learning offers a way to study how communication could emerge in communities of agents needing to solve specific problems. In this paper, we study the eme…
Quixer: A Quantum Transformer Model
Nikhil Khatri, Gabriel Matos, Luuk Coopmans +1
Progress in the realisation of reliable large-scale quantum computers has motivated research into the design of quantum machine learning models. We present Quixer: a novel quantum…
Formalising and Learning a Quantum Model of Concepts
Sean Tull, Razin A. Shaikh, Sara Sabrina Zemljic +1
In this report we present a new modelling framework for concepts based on quantum theory, and demonstrate how the conceptual representations can be learned automatically from data.…
Mathematical Foundations for a Compositional Distributional Model of Meaning
Bob Coecke, Mehrnoosh Sadrzadeh, Stephen Clark
We propose a mathematical framework for a unification of the distributional theory of meaning in terms of vector space models, and a compositional theory for grammatical types, for…
Automated near-term quantum algorithm discovery for molecular ground states
Fabian Finger, Frederic Rapp, Pranav Kalidindi +10
Designing quantum algorithms is a complex and counterintuitive task, making it an ideal candidate for AI-driven algorithm discovery. To this end, we employ the Hive, an AI platform…
Principal Solutions Revisited
Stephen Clark, Fritz Gesztesy, Roger Nichols
The main objective of this paper is to identify principal solutions associated with Sturm-Liouville operators on arbitrary open intervals , as introduce…
From Conceptual Spaces to Quantum Concepts: Formalising and Learning Structured Conceptual Models
Sean Tull, Razin A. Shaikh, Sara Sabrina Zemljic +1
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 representat…
Unconditional preparation of entanglement between atoms in cascaded optical cavities
Stephen Clark, Amy Peng, Mile Gu +1
We propose a scheme to unconditionally entangle the internal states of atoms trapped in separate high finesse optical cavities. The scheme uses the technique of quantum reservoir e…
Factorising AMR generation through syntax
Kris Cao, Stephen Clark
Generating from Abstract Meaning Representation (AMR) is an underspecified problem, as many syntactic decisions are not constrained by the semantic graph. To explicitly account for…
Particle production from Q-balls
Stephen Clark
Non topological solitons, Q-balls can arise in many particle theories with U(1) global symmetries. As was shown by Cohen et al. \cite{Qballscohen}, if the corresponding scalar fiel…
Learning Type-Driven Tensor-Based Meaning Representations
Tamara Polajnar, Luana Fagarasan, Stephen Clark
This paper investigates the learning of 3rd-order tensors representing the semantics of transitive verbs. The meaning representations are part of a type-driven tensor-based semanti…
Learning Complex Word Embeddings in Classical and Quantum Spaces
Carys Harvey, Stephen Clark, Douglas Brown +1
We present a variety of methods for training complex-valued word embeddings, based on the classical Skip-gram model, with a straightforward adaptation simply replacing the real-val…
Latent Variable Dialogue Models and their Diversity
Kris Cao, Stephen Clark
We present a dialogue generation model that directly captures the variability in possible responses to a given input, which reduces the `boring output' issue of deterministic dialo…
The Frobenius anatomy of word meanings II: possessive relative pronouns
Mehrnoosh Sadrzadeh, Stephen Clark, Bob Coecke
Within the categorical compositional distributional model of meaning, we provide semantic interpretations for the subject and object roles of the possessive relative pronoun `whose…
Learning to Prepare Molecular Ground States with Transformer Models
Alex Koziell-Pipe, Jasmine Brewer, Jem Guhit +14
Quantum state preparation is a key component of many quantum algorithms. Performing this step efficiently is essential for realizing practical quantum advantage in quantum chemistr…
Characterization of self-adjoint extensions for discrete symplectic systems
Petr Zemánek, Stephen Clark
All self-adjoint extensions of minimal linear relation associated with the discrete symplectic system are characterized. Especially, for the scalar case on a finite discrete interv…
Boundary Data Maps for Schrodinger Operators on a Compact Interval
Stephen Clark, Fritz Gesztesy, Marius Mitrea
We provide a systematic study of boundary data maps, that is, 2 \times 2 matrix-valued Dirichlet-to-Neumann and more generally, Robin-to-Robin maps, associated with one-dimensional…
Weyl-Titchmarsh Theory and Borg-Marchenko-type Uniqueness Results for CMV Operators with Matrix-Valued Verblunsky Coefficients
Stephen Clark, Fritz Gesztesy, Maxim Zinchenko
We prove local and global versions of Borg-Marchenko-type uniqueness theorems for half-lattice and full-lattice CMV operators (CMV for Cantero, Moral, and Velazquez) with matrix-va…
Minimal Rank Decoupling of Full-Lattice CMV Operators with Scalar- and Matrix-Valued Verblunsky Coefficients
Stephen Clark, Fritz Gesztesy, Maxim Zinchenko
Relations between half- and full-lattice CMV operators with scalar- and matrix-valued Verblunsky coefficients are investigated. In particular, the decoupling of full-lattice CMV op…
Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input
Angeliki Lazaridou, Karl Moritz Hermann, Karl Tuyls +1
The ability of algorithms to evolve or learn (compositional) communication protocols has traditionally been studied in the language evolution literature through the use of emergent…
The Conceptual VAE
Razin A. Shaikh, Sara Sabrina Zemljic, Sean Tull +1
In this report we present a new model of concepts, based on the framework of variational autoencoders, which is designed to have attractive properties such as factored conceptual d…
Grounded Language Learning Fast and Slow
Felix Hill, Olivier Tieleman, Tamara von Glehn +3
Recent work has shown that large text-based neural language models, trained with conventional supervised learning objectives, acquire a surprising propensity for few- and one-shot…
Latent Tree Learning with Differentiable Parsers: Shift-Reduce Parsing and Chart Parsing
Jean Maillard, Stephen Clark
Latent tree learning models represent sentences by composing their words according to an induced parse tree, all based on a downstream task. These models often outperform baselines…
On discrete symplectic systems: Associated maximal and minimal linear relations and nonhomogeneous problems
Stephen Clark, Petr Zemánek
In this paper we characterize the definiteness of the discrete symplectic system, study a nonhomogeneous discrete symplectic system, and introduce the minimal and maximal linear re…
Property Classification of Vacation Rental Properties during Covid-19
Favour Yahdii Aghaebe, Dustin Foley, Eric Atwell +1
This study advocates for employing clustering techniques to classify vacation rental properties active during the Covid pandemic to identify inherent patterns and behaviours. The d…
Who voted for a No Deal Brexit? A Composition Model of Great Britains 2019 European Parliamentary Elections
Stephen Clark
The purpose of this paper is to use the votes cast at the 2019 European elections held in United Kingdom to re-visit the analysis conducted subsequent to its 2016 European Union re…