Published: 21 February 2022

CTS announces recruitment process for a post-doctoral researcher in NLP for legal documents

The Centre for Translation Studies is looking for a new post-doctoral researcher to work with Natural Language Processing for legal documents in their new Innovate UK project in collaboration with JUST: Access.

Applications are invited for a 16 month research fellow position in Natural Language Processing for legal documents to work on a project funded by Innovate UK entitled "Harnessing court data using NLP and spoken language technology". This is a fix term, part time position. The successful post holder is expected to start on 1 May 2022 or as soon as possible thereafter and will be based in the Centre for Translation Studies reporting to the project PI (Prof Orasan).

The aim of the project is to develop in collaboration with JUST: Access, a not-for-profit social enterprise, the very first automated transcription tool designed specifically for the Justice sector. We will build on the work that JUST:access has already carried out to develop an interface which enables them to provide high quality legal transcription of audio and video using off-the-shelf STT and a pool of law-student-editors to edit the automated transcription. In this project we will incorporate NLP techniques in the current interface in order to make the process of correcting transcripts less demanding. In addition, NLP technology will be used to link automatic transcripts with related texts documents in order to provide ways of making them more easily navigable and searchable. 

The post holder will be responsible for designing and developing NLP based methods for correcting recurring errors in the automatic transcription and provide ways to link the automatic transcriptions to related documents. They will work closely with Prof Orasan and JUST: Access to assess the suitability of the developed solutions.

The successful applicant is expected to have a PhD (gained or near completion) or equivalent professional experience in NLP, computer science or linguistics, with proven experience of applied NLP. Experience in one or more of the following areas is necessary: machine learning for NLP, deep learning, using transformer based models for language processing, named entity recognition, speech processing, automatic speech recognition, information retrieval. Good programming experience in Python and proven use of relevant NLP libraries like Spacy is desirable. Interdisciplinary research experience will also be desirable.

More information is available at the University of Surrey's Job Opportunities page, where it is also possible to apply for this position. The deadline for applications is on the 21st of March 2022 at 23:59 GMT.