Jonathan Mallinson
Data Science PhD
Tell Me More

About me

NLP PhD Student. Focusing on semantics and text generation.

Hello, I am Jonathan. I am doing my PhD at the University of Edinburgh under the supervision of Mirella Lapata and Rico Sennrich. My main interest is text generation; in particular paraphrasing and sentence compression. I am funded by EPSRC's CDT in Data Science program. Before coming to Edinburgh I was at the University of Amsterdam where I did a masters in logic. Previously, I studied Computer Science at the Unversity of Birmingham.

Projects

A list of ideas I've worked on.

Papers

2017 Paraphrasing Revisited with Neural Machine Translation.

Jonathan Mallinson; Rico Sennrich; Mirella Lapata (2017). In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics, Valencia, Spain.

Revisiting bilingual pivoting in the context of neural machine translation and presenting a paraphrasing model based purely on neural networks. Our model represents paraphrases in a continuous space, estimates the degree of semantic relatedness between text segments of arbitrary length, or generates candidate paraphrases for any source input.

Dissertations

2016 PARANET: Bilingual Encoder-Decoder Paraphrasing

MSc(R) in Data Science.

I explored in detail how neural machine translation can be used to paraphrase. This dissertation formed the basis of my paper "Paraphrasing Revisited with Neural Machine Translation". Supervisor: Mirella Lapata

2015 Modelling Syntactic and Semantic Tasks with Linguistically Enriched Recursive Neural Networks

MSc in Logic.

Recursive Neural Networks, enhanced with linguistically motivated features were successfully used as a syntactic parser and paraphrase detector. Supervisor: Willem (Jelle) Zuidema

2011 Simulated Stock Market using Fuzzy Agents

BSc in Computer Science.

Multi-agent modeling of the stock market, agents used fuzzy logic for decision making. Evolutionary learning was applied to minimise the objective function. Supervisor: Antoni Diller

Accredited Projects

2015 Sentiment analysis using flat trees

I explored the effect of flattening syntactic trees found within the Sentiment Treebank. Supervisor: Charles Sutton

2015 Unsupervised semantic role labelling with constraints

Expectation maximization (EM) was used to train HMM parametrised with features, under constraints imposed by VerbNet, to learn semantic roles in an unsupervised approach. Supervisor: Ivan Titov

2014 Predicting the meaning in use of occurrences of Fall

Working in a team of researchers I helped to provide a data-based semantic/pragmatic analysis of "FALL". Supervisor: Henk Zeevat

2012 Lexical simplification - Data Augmentation

Augmentation of the Semeval 2012 lexical simplification dataset was found to improve upon the baseline system. Supervisor: Raquel Fernández

Education

The places I've been and the programs I've taken

  • 2016-2019

    Data Science PhD

    The University of Edinburgh

    I'm currently enjoying my first year of my PhD.

  • 2015-2016

    Data Science MSc(R)

    Distinction
    The University of Edinburgh

    I completed a one year research masters in Data Science. My studies focused on a mix of Machine learning and NLP.

  • 2012-2015

    Logic MSc

    8 (Distinction equivalent)
    The University of Amsterdam

    I took a Masters in Logic, taking the "logic & language" track. Which included learning a mix of semantics, NLP and linguistics.

  • 2008-2011

    Computer Science BSc

    First class honors
    The University of Birgmingham

    I spent three years at the University of Birmingham studying Computer Science.

Contact Details

To get in touch...

Email
J.Mallinson@ed.ac.uk

Address
Room 3.33, Informatics Forum
10 Crichton Street
Edinburgh, UK
EH8 8BQ