AT4SSL 2025 : Third International Workshop on Automatic Translation for Sign and Spoken Languages
Third International Workshop on Automatic Translation for Signed and Spoken Languages (AT4SSL2025 @MTSummit2025)
Call For Papers
SCOPE
Machine translation (MT) is a core technique for reducing language barriers and is being used in the workflow of professional translation and in every-day life by content consumers. MT has come a long way since its inception in the 1950s with today's large language models, capable of translation surpassing the quality of specialized NMT models for many use-cases. But when it comes to automatically translating between signed and spoken languages (SpL), the current technology is still not capable of effectively filling in the communication vacuum. The complexity of the task to automatically translate between SLs or SL and spoken languages, requires a multidisciplinary approach.
The rapid technological and methodological advances in deep learning, and in AI in general, that we see in the last decade, have not only improved MT, recognition of image, video and audio signals, the understanding of language, the synthesis of life-like 3D avatars, etc., but have also led to the fusion of interdisciplinary research innovations that lays the foundation of automated translation services between sign and spoken languages.
This workshop aims to be a venue for presenting and discussing (complete, ongoing or future) research on automatic translation between sign and spoken languages and outline the potential future in the research and development of the field.
As with the first and second editions, this one-day workshop will bring together researchers, practitioners, interpreters and innovators who focus on SL linguistics, MT, natural language processing (NLP), interpreting of sign and spoken languages, image and video recognition (for the purpose of sign language recognition), 3D avatar and virtual signers synthesis, and other related fields, to discuss problems, challenges and opportunities for the automated and computer-assisted translation of sign-to-spoken, spoken-to-sign and sign-to-sign communication.
THEME OF THE WORKSHOP
Data has assumed a vital role in the development of AI models, including NMT and LLMs. The scarcity of SL data, which hurdles the development of models of sufficient quality, has been and continues to be a challenge that requires the extensive involvement of signers. In addition, many prior works on SL NLP and MT have not included the deaf community or have done so in an ineffective and sometimes unethical way. In this edition of the workshop we want to focus on the topic of Co-creation for positive impact.
TOPICS
This workshop aims to focus on the following topics. However, submissions related to the general topic of automatic translation between signed and spoken languages that deviate from these topics are also welcome:
Data: resources, collection and curation, challenges, processing, data life cycle
Use-cases, applications
User and user involvement
Ethics, privacy and policies
Sign language linguistics
Machine translation (with a focus on signed-to-signed, signed-to-spoken or spoken-to-signed language translation)
Natural language processing
Interpreting of sign and spoken languages
Image and video recognition (for the purpose of sign language recognition)
3D avatar and virtual signers synthesis
Usability and challenges of current methods and methodologies
Sign language in the media
SUBMISSION FORMAT
Two types of submissions are going to be accepted for the AT4SSL workshop:
Research, review, position and application papers.
Unpublished papers that present original, completed work. The length of each paper should be at least four (4) and maximum eight (8) pages, with unlimited pages for references.
Extended abstracts should present original, ongoing work or innovative ideas, including ongoing or recently finished project descriptions. The length of each extended abstract is four (4) pages, with unlimited pages for references.
Both type of papers should be formatted according to the official MT Summit 2025 style templates (LaTex. Overleaf, MS Word, PDF).
Accepted papers and extended abstracts will be published in the MT Summit 2025 proceedings and will be presented at the conference.
SUBMISSION POLICY
Submissions must be anonymized.
Papers and extended abstracts should be submitted using EASY Chair (more information will follow).
Work that has been or is planned to be submitted to other venues must be declared as such. Upon acceptance at AT4SSL, it must be withdrawn from the other venues.
The review will be double-blind.
IMPORTANT DATES:
First call for papers: 20 December 2024
Second call for papers: 24 January 2025
Submission deadline: 10 March 2025
Acceptance notification 31 March 2025
Camera-ready due: 07 April 2025
Submission of material for interpreters: 13 June 2025
Workshop date: 24 June 2025
ORGANISATION COMMITTEE:
Dimitar Shterionov (TiU)
Mirella De Sisto (TiU)
Vincent Vandeghinste (KU Leuven; INT)
Victoria Nyst (Leiden University)
Myriam Vermeerbergen (KU Leuven)
Floris Roelofsen (UvA)
Bram Vanroy (KU Leuven; UGent)
Lisa Lepp (TiU)
Irene Strasly (UniGe)
INTERPRETING:
We will provide interpreting between English and International Sign (IS) during the workshop.
FOR CONTACTS:
Dimitar Shterionov, workshop chair: [email protected]
Registration will be handled by the MTSummit 2025 conference. (To be announced)
Call For Papers
SCOPE
Machine translation (MT) is a core technique for reducing language barriers and is being used in the workflow of professional translation and in every-day life by content consumers. MT has come a long way since its inception in the 1950s with today's large language models, capable of translation surpassing the quality of specialized NMT models for many use-cases. But when it comes to automatically translating between signed and spoken languages (SpL), the current technology is still not capable of effectively filling in the communication vacuum. The complexity of the task to automatically translate between SLs or SL and spoken languages, requires a multidisciplinary approach.
The rapid technological and methodological advances in deep learning, and in AI in general, that we see in the last decade, have not only improved MT, recognition of image, video and audio signals, the understanding of language, the synthesis of life-like 3D avatars, etc., but have also led to the fusion of interdisciplinary research innovations that lays the foundation of automated translation services between sign and spoken languages.
This workshop aims to be a venue for presenting and discussing (complete, ongoing or future) research on automatic translation between sign and spoken languages and outline the potential future in the research and development of the field.
As with the first and second editions, this one-day workshop will bring together researchers, practitioners, interpreters and innovators who focus on SL linguistics, MT, natural language processing (NLP), interpreting of sign and spoken languages, image and video recognition (for the purpose of sign language recognition), 3D avatar and virtual signers synthesis, and other related fields, to discuss problems, challenges and opportunities for the automated and computer-assisted translation of sign-to-spoken, spoken-to-sign and sign-to-sign communication.
THEME OF THE WORKSHOP
Data has assumed a vital role in the development of AI models, including NMT and LLMs. The scarcity of SL data, which hurdles the development of models of sufficient quality, has been and continues to be a challenge that requires the extensive involvement of signers. In addition, many prior works on SL NLP and MT have not included the deaf community or have done so in an ineffective and sometimes unethical way. In this edition of the workshop we want to focus on the topic of Co-creation for positive impact.
TOPICS
This workshop aims to focus on the following topics. However, submissions related to the general topic of automatic translation between signed and spoken languages that deviate from these topics are also welcome:
Data: resources, collection and curation, challenges, processing, data life cycle
Use-cases, applications
User and user involvement
Ethics, privacy and policies
Sign language linguistics
Machine translation (with a focus on signed-to-signed, signed-to-spoken or spoken-to-signed language translation)
Natural language processing
Interpreting of sign and spoken languages
Image and video recognition (for the purpose of sign language recognition)
3D avatar and virtual signers synthesis
Usability and challenges of current methods and methodologies
Sign language in the media
SUBMISSION FORMAT
Two types of submissions are going to be accepted for the AT4SSL workshop:
Research, review, position and application papers.
Unpublished papers that present original, completed work. The length of each paper should be at least four (4) and maximum eight (8) pages, with unlimited pages for references.
Extended abstracts should present original, ongoing work or innovative ideas, including ongoing or recently finished project descriptions. The length of each extended abstract is four (4) pages, with unlimited pages for references.
Both type of papers should be formatted according to the official MT Summit 2025 style templates (LaTex. Overleaf, MS Word, PDF).
Accepted papers and extended abstracts will be published in the MT Summit 2025 proceedings and will be presented at the conference.
SUBMISSION POLICY
Submissions must be anonymized.
Papers and extended abstracts should be submitted using EASY Chair (more information will follow).
Work that has been or is planned to be submitted to other venues must be declared as such. Upon acceptance at AT4SSL, it must be withdrawn from the other venues.
The review will be double-blind.
IMPORTANT DATES:
First call for papers: 20 December 2024
Second call for papers: 24 January 2025
Submission deadline: 10 March 2025
Acceptance notification 31 March 2025
Camera-ready due: 07 April 2025
Submission of material for interpreters: 13 June 2025
Workshop date: 24 June 2025
ORGANISATION COMMITTEE:
Dimitar Shterionov (TiU)
Mirella De Sisto (TiU)
Vincent Vandeghinste (KU Leuven; INT)
Victoria Nyst (Leiden University)
Myriam Vermeerbergen (KU Leuven)
Floris Roelofsen (UvA)
Bram Vanroy (KU Leuven; UGent)
Lisa Lepp (TiU)
Irene Strasly (UniGe)
INTERPRETING:
We will provide interpreting between English and International Sign (IS) during the workshop.
FOR CONTACTS:
Dimitar Shterionov, workshop chair: [email protected]
Registration will be handled by the MTSummit 2025 conference. (To be announced)