QNLP in Practice: Running Compositional Models of Meaning on a Quantum Computer

In this paper, we present results on the first NLP experiments conducted on Noisy Intermediate-Scale Quantum computers for datasets of size ≥ 100 sentences. We use representations for sentences that have a natural mapping to quantum circuits to implement and successfully train two NLP models that solve simple sentence classification tasks on quantum hardware.

Download PDF

Grammar Equations

This work paves the way for a new theory of grammar that provides novel “grammatical truths.” We give a nogo-theorem for the fact that our wirings for words make no sense for preordered monoids, the form which grammatical calculi usually take. Instead, they require diagrams – or equivalently, (free) monoidal categories.

Download PDF

A Non-Anyonic Qudit ZW-calculus

We give a new type of qudit ZW-calculus which has generators and rewriting rules similar to that of the qubit ZW-calculus. Furthermore, we establish a translation between this qudit ZW-calculus and the qudit ZX-calculus which is universal. Therefore, this qudit ZW-calculus is also universal for pure qudit quantum computing.

Read Publication
Download PDF

Something Old, Something New: Grammar-Based CCG Parsing with Transformer Models

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 to substantial gains over existing approaches. The report provides a minimal introduction to CCG and CCG parsing, with many pointers to the relevant literature. It then describes the CCG supertagging problem and some recent work from Tian et al. (2020) which applies Transformer-based models to supertagging with great effect.

Download PDF

Kindergarten Quantum Mechanics Graduates

This paper is a “spiritual child” of the 2005 lecture notes Kindergarten Quantum Mechanics, which showed how a simple, pictorial extension of Dirac notation allowed several quantum features to be easily expressed and derived, using language even a kindergartener can understand.

Download PDF

A CCG-Based Version of the DisCoCat Framework

The DisCoCat model has proved to be a valuable tool for studying compositional aspects of language. However, the strong dependency of the model on a specific grammar formalism, gives rise to both theoretical and practical problems. We solve these problems by reformulating DisCoCat as a passage from Combinatory Categorial Grammar (CCG) to a category of semantics.

Download PDF