Postgraduate Research Opportunity

Analysing and understanding multisource and multipurpose unstructured data using deep learning

Details

Title: SH18: Analysing and understanding multisource and multipurpose unstructured data using deep learning

Funding: Full time Home/EU/overseas fees and a stipend of £15,009 p.a. (further fee details)

Application deadline: 17 June 2019

Start date: October 2019

Duration: 3 years (full time)

Location: Colchester Campus

Based in: School of Computer Science and Electronic Engineering

This studentship is now closed. See our current opportunities.

Overview

Many companies with significant workforces of field engineers, desk-based agents and multi-channel customer support services (phone, email, online chat, etc.) have to collect and manage large volumes of unstructured information and semi-structured information to operate their businesses.

As such, British Telecom (BT) has a long-term record of field engineers’ notes, technical documents and unstructured question-answering databases for problem solving. Common to these sources of information is that it usually comes as free-form text, that is unstructured and thus difficult to access.

However, the information is of huge business value as it contains important explicit and implicit information about specific pieces of work and customer services. The extraction of structured information from this BT databases has been a slow and labour-intensive due to manual activity in many cases up to now, and that has limited full exploitation of this information.

The project

The PhD studentship aims to address this challenge with automated text analyses using modern machine learning methods, most importantly Deep Learning techniques.

The studentship may extract relevant entities and events from the text and contextualise this information in a semantic semi-structured knowledge base. This will enable to exploit the information in the newly created and continuously updated knowledge base for new services in question-answering related use cases.

As such, we are particularly interested in PhD candidates that like to work on one or multiple of the following topics:

  • Temporal extraction of semi-structured knowledge such as entities and events from text data.
  • Semantic question answering systems using Deep Learning.
  • Knowledge capturing and knowledge graphs building from textual sources.
  • Sentiment analysis and automated classification of tasks from unstructured data.

The PhD project aims to investigate the topic to support BT business operating models, focusing on text analysis and data analysis. 

The studentship will be part of the Natural Language and Information Processing (NLIP) research group in the School of Computer Science and Electronic Engineering (CSEE) at the University of Essex.

The successful candidate will have the opportunity and be expected to partially work at BT’s research and development site at Adastral Park, Ipswich in order to run large-scale experiments on BT’s data sets.

Funding

The award consists of a full Home/EU/overseas fee waiver (further fee details), a doctoral stipend equivalent to the Research Councils UK National Minimum Doctoral Stipend (£15,009 in 2019-20), plus £2,500 training bursary via Proficio funding, which may be used to cover the cost of advanced skills training including conference attendance and travel.

Criteria

At a minimum, the successful applicant will have a good honours BSc degree (1st class or high 2:1, or equivalent) in computer science or related subjects. An MSc with Merit or Distinction is desirable (but not essential for students with a first class degree).

Strong analytical and mathematical skills are required, as well as good programming skills.

Essential skills

This role requires the following capabilities:

  • Qualified to graduate level with experience in computer science, artificial intelligence, data science.
  • A creative and innovative approach to solving complex technical problems.
  • Good to very good programming skill in any modern language (e.g., Python, Java, …) is essential

Understanding and/or experience in/of

  • Research problems and application of rigid scientific methodologies to problem solving
  • Deep Learning methods, preferably in text analysis
  • Software engineering principles, technologies and frameworks in developing reusable components.
  • An inquiring mind with a preference for working within less defined boundaries, excellent creativity, self-motivation and good written and oral communication skills, and must be passionate about achieving excellent results.

How to apply

You can apply for this postgraduate research opportunity online.

Please include your CV, covering letter, personal statement, and transcripts of UG and Masters degrees in your application.

The University has moved to requiring only one reference for PhD applications and these can be received after a conditional offer has been made so the absence of these will not hold up the recruitment process.

Instruction to applicants

When you apply online you will be prompted to fill out several boxes in the form:

  • For "Course title" please put "PhD Computer Science"
  • For "Proposed research topic or area of research" please put the title of this studentship (SH18: Analysing and understanding multisource and multipurpose unstructured data using deep learning)
  • For "If you have contacted a potential supervisor..." please put Professor Ansgar Scherp.

If you have any informal queries about this opportunity please email the supervisor, Professor Ansgar Scherp (ansgar.scherp@essex.ac.uk)