LINGUIST List 24.2380

Mon Jun 10 2013

Jobs: Comp Ling; NLP: Post Doc, University of Edinburgh

Editor for this issue: Caylen Cole-Hazel <>

Date: 10-Jun-2013
From: Charles Sutton <>
Subject: Computational Linguistics; Natural Language Processing: Post Doc, University of Edinburgh, Edinburgh, United Kingdom
E-mail this message to a friend

University or Organization: University of EdinburghDepartment: School of InformaticsJob Location: Edinburgh, United KingdomWeb Address: Rank: Post Doc

Specialty Areas: Computational Linguistics; Natural Language Processing


The School of Informatics at the University of Edinburgh is seeking anexcellent post doctoral research associate for a new EPSRC-funded project toapply methods from statistical natural language processing and data mining tofind patterns in computer program source code. The project is supervised by Dr.Charles Sutton.

Modern software developers often find it necessary to use software librariesand programming languages with which they are unfamiliar, which can lead tolonger development times and lower reliability. However, on the Internetbillions of lines of open source code are readily available, code thatcontains a large amount of implicit knowledge about good coding practice. Thegoal of the project is to find patterns in large corpora of source code text,which can be used to help developers to write better code, in effecttransferring knowledge from experienced developers to less experienceddevelopers.

Like natural language, programming languages are a means of humancommunication: experienced programmers know that they are writing as much forother programmers as for the computer. This raises the exciting possibilitythat many aspects of programming language text can be just as amenable tostatistical analysis as natural language has been. But unlike naturallanguage, statistical analysis of programming language text is an area in itsinfancy. This is a new domain for NLP, with many opportunities for developingadvanced new probabilistic models and machine learning algorithms.

The successful candidate will have a background in statistical languageprocessing or machine learning and a strong interest in the application area.We will also consider applications from researchers in software engineeringwho have strong interest in building their knowledge of techniques fromstatistical NLP and machine learning. This is a new application area, so we donot expect that candidates will have worked on both ML/NLP and source code.

The researcher will be a part of the School of Informatics at the Universityof Edinburgh. This is an opportunity to work in a world-leading groups formachine learning and NLP. More broadly, a recent international reviewdescribed the School as an "elite" department of computer science in Europe,and in national research assessment exercises, the School of Informatics hasconsistently ranked at the top in the UK for research quality.

Application Deadline: 19-Jul-2013

Web Address for Applications: Information: Charles Sutton Email:

Page Updated: 10-Jun-2013