Linguistics Research

Find out about the latest and ongoing research at our centre.

A list of projects by key contact

Key contact: Prof. Kearsy Cormier

SignGPT is an EPSRC-funded five year collaboration between DCAL, University of Oxford, and University of Surrey, pooling their expertise and experience in sign language linguistics, computational linguistics, computer vision, and machine learning. Objectives for the project include the development of tools to recognise and classify human motion as BSL signs; tools for automatically generating synthetic but natural-looking BSL; two-way translation tools between BSL and English; tools that enable videos of BSL to be searched for specific signs or meanings; and to collect and curate massive datasets that will further support the development of Large Language Models for BSL.

Additional key contact: Prof. Bencie Woll

SignGPT FAQ

In the long term, we want to create AI chatbots for BSL and other sign languages. This would be something like ChatGPT or Gemini, except that you would ask questions directly in BSL, and get a response from a generated avatar that looks and signs like a real person. For example, you could use it to summarise a signed video or a text web page in BSL. To get to that point, there are two problems to solve:

  • Teaching computers to recognise BSL from video input (e.g. a webcam)
  • Producing realistic and believable signing on the screen (so a computer can reply in BSL without using English at any stage)

To solve these problems, we need systems based on high quality sign language data. But to get that high quality data, we first need better visual language “tools”.

These are important issues. If we want high quality sign language AI, we need high quality data that is diverse but also well organised. Simply scraping random videos off the internet is not good enough. SignGPT prioritises BSL video data which represents different UK regions, different age groups, and different ethnic backgrounds. We also make a distinction between deaf and hearing signers, and between spontaneous and interpreted signing.

No! This kind of technology is not a replacement for human interpreters. We believe that human interpreters are essential, especially for complex, sensitive, or high-stakes communication. This project focuses on everyday low risk situations where an interpreter isn’t practical. We think that people should be free to choose whether or not they want to use technology to help with everyday communication.

Deaf BSL users are involved at every level, not just as participants. They are:

  • Members of the research teams
  • Members of the Advisory Board
  • Central to planning, designing, testing and evaluation

The project is built on the idea that technology for BSL must be co-created with the Deaf community, otherwise it will not be trusted or useful.

  • Understanding the history of British Sign Language variation and change through deaf school records in the UK

This project examines the regional origins and mobility of deaf pupils in the earliest UK schools, focusing in particular on the London Asylum School, founded in 1792, and analysing its first 50 years of records. Using archival school registers, the study aims to trace historical patterns of variation and change in BSL. Following the methods of Power & Meier (2023), which investigate demographic and regional factors in early U.S. schools for the deaf, it will compare the mobility of 19th-century BSL signers with that of American Sign Language (ASL) signers.

This is a collaborative work carried out by researchers from the UK and the USA.

Additional key contact: Prof. Bencie Woll

EASIER is a Horizon 2020 (EU) project that aims to design, develop, and validate a complete multilingual machine translation system that will act as a framework for barrier-free communication among deaf and hearing individuals, as well as provide a platform to support sign language content creation.

ExTOL, funded by the Engingeering and Physical Sciences Research Council, aims to take annotated sign language corpus data and to use this to build a system that is capable of watching a human signing and turning this into written English. In the process, this project will also create computer vision tools to assist with video analysis.

Additional key contact: Prof. Bencie Woll

This project, funded by the Economic and Social Research Council, aims to study how languages can start from scratch, and to see how the languages we know today could have gotten their rules and their rich structure, with focus on word order.

This project, funded by the Arts and Humanities Research Council, aims to document and describe word order and non-manual features in different types of BSL sentences, using the BSL Corpus.

This project, funded by the Economic and Social Research Council, aims to investigate how deaf signers of BSL mimetically reproduce the actions, utterances, thoughts and feelings of themselves, other people, animals and things, using existing conversation and personal narrative data in the BSL Corpus.

This project, funded by the Economic and Social Research Council, aims to study language attitudes and language awareness in the British Deaf community, using interview data from the BSL Corpus.

Additional key contact: Dr. Kate Rowley

BSL SignBank is DCAL’s online British Sign Language dictionary, created from signs used in the BSL Corpus. Funding for creation of BSL SignBank finished in 2016 but work on the dictionary continues.

Additional key contact: Prof. Bencie Woll and Dr. Kate Rowley

The British Sign Language (BSL) Corpus is a large collection of video clips showing Deaf people using BSL, with metadata and ELAN annotations. Funding for creation of the BSL Corpus finished in 2011 but work on the corpus continues.

Additional key contact: Prof. Bencie Woll

Key contact: Dr. Robert Adam

Australian Irish Sign Language (AISL) is a minority sign language within a minority sign language community brought to Australia from Ireland in 1875. Most signers are in their early 70s onwards and they number 100 although there may be younger Deaf & hearing native signers with Deaf parents.

Key contact: Prof. Bencie Woll

  • Bilingualism in deaf and hearing people: learning and neuroplastic processes

The studies involve the investigation of unimodal and bimodal bilingualism, examining both spoken and signed languages (Russian Sign Language and British Sign Language). A mix of linguistic, psycholinguistic and neuroscience approaches are used to address bilingualism in hearing and deaf people - specifically, the effects of modality on language learning and language processing - by exploring the differences between learning a second language in the same modality compared to learning a second language in a new modality.

This British Academy Special Research Project is part of the British Academy’s initiative to deepen awareness and demonstrate the importance of languages. This project is concerned with language learning in relation to cognitive function across the lifespan, including modern and community language education, language skills, employment/ability, community cohesion, and public policy, and explores cross-curriculum and cross-societal benefits to individuals and various SEC groups.