First Call for Participation

first_cfp_iwslt_2020.pdf

EVALUATION

IWSLT 2020 will feature five challenges that address the following focus areas:

  • End-to-end SLT models (Chair: M. Turchi, FBK) – overcoming the cascaded approach
  • Simultaneous translation (Chair: J. Gu, Facebook) – low latency, real-time interpretation
  • Conversational speech translation (Chair: E. Salesky, JHU) – highly disfluent speech
  • Open domain translation (Chair: A. Nagesh, Didi Labs) – new domains and languages
  • Non-native speech translation (Chair: O. Bojar, Charles U.) – non-native disfluent speech

Training and development data for each challenge will be released. Organizers will provide baseline component systems to participants that do not have access to an individual component. Human and automatic scoring will be performed on each challenge, published and discussed. An opportunity for secondary system submissions will be given in the week following primary submissions.

CONFERENCE

IWSLT invites submissions of workshop sessions for focused presentations and discussions, as well as scientific papers to be published in the proceedings and presented either in oral or poster format. The conference selects high quality, original contributions on theoretical and practical issues of automatic speech recognition (ASR), machine translation (MT) speech synthesis (TTS) pertaining to spoken language translation (SLT). More specific topics include:

  • Approaches and performance
  • End-to-end models
  • Evaluation, metrics, benchmarks, usability
  • Paralinguistic aspects in interpretation
  • Language resources
  • Open source software
  • Multilingual approaches
  • Sign language translation
  • Under-resourced languages
  • Multimodal Interfaces
  • Architectures
  • Adaptation
  • Post- and pre-processing
  • Efficiency, speed, latency
  • Applications
  • Discourse and context aware translation

IMPORTANT DATES

Evaluation Campaign Scientific Program
January 2020: release of train and dev data January 15, 2020: proposal of workshop sessions
March 2020: evaluation period January 24 2020: workshop session notification
April 6th 2020: system description paper due April 6, 2020: paper submission deadline
May 4th 2020: review feedback May 4, 2020: paper notification
May 18th 2020: camera-ready paper due May 18, 2020: camera-ready version due