EPSRC Funded Studentship: Composition and Entailment in Distributed Word Representations (2018)

What you get

You will receive:

• Home/EU PhD fees
• a tax-free living expenses at Research Council UK rates (£14,777 per year for 2018/19)
• research/training expenses for three and a half years.

Type of award

PhD

PhD project

One of the fundamental challenges in Natural Language Processing is the variety of expression permitted in English or any natural language.

For example, there are vast numbers of words in any vocabulary and it is naïve to treat these as having completely distinct meanings.

Distributed word representations, which represent each word in terms of it's co-occurrences with other words, have long promised (Lee (1999),Weeds(2005)) to be useful in tackling this problem since they capture the similarity or relationships between the meanings of words in a continuous space.

The rise of neural network methods for learning low dimensional distributed word representations, since Mikolov's seminal work on Word2Vec (Mikolov(2013)), has further increased the popularity of work in this area with applications being made in all areas of Natural Language Processing, including speech recognition, question-answering and machine translation.

However, a number of questions remain unanswered; two of which will be considered in this project.

First, distributed word representations tend to conflate a large number of different semantic relations including synonymy, antonymy and hyponymy; which may be appropriate in some but not all applications. Therefore, how can these different relations be distinguished?

Second, given distributed representations of words, what is the most appropriate way to combine them to represent larger units of meaning such as phrases and sentences?

These two questions are in fact related since the meaning of a phrase has a semantic relation with the meaning of each of its components. For example, a 'sweet fruit' is a 'fruit' and can be seen as a hyponym of 'fruit'.

This project will therefore explore the interaction between composition and lexical entailment in distributed word representations.

Eligibility

To be eligible, you need to have:

• an excellent academic record and should have received or be expected to receive a relevant first or upper-second class honours degree.
• be a UK or EU student who has been ordinarily resident in the UK for the previous 3 years. If you are an EU candidate and you don't meet this criteria, you are only eligible for a fee waiver 
• good programming skills in at least one of Python/Java/C/C++ (essential)
• experience in Natural Language Processing / Computational Linguistics (essential).

Experience in Machine Learning is also desirable.

If you are an overseas (non EU) student, you are not eligible to apply.

Deadline

30 June 2018 0:00

How to apply

You need to apply for a PhD in Informatics through the University of Sussex postgraduate application system.

When you apply, include a brief statement of your scientific interests and skills/experience for the mandatory "research proposal" section, including how they relate to this project (maximum two pages).

You should also indicate Dr Julie Weeds as your preferred advisor and clearly state the title of the studentship in the finance section.

Contact us

Email Dr Julie Weeds at J.E.Weeds@sussex.ac.uk

Timetable

The deadline is 02/03/2018.