The International Workshop on Spoken Language Translation (IWSLT) is a yearly scientific workshop, associated with an open evaluation campaign on spoken language translation, where both scientific papers and system descriptions are presented. The 14th International Workshop on Spoken Language Translation will take place in Tokyo, Japan, on December 14-15, 2017.
Evaluation Campaign
IWSLT 2017 will offer three official evaluation tasks: multilingual text translation of TED talks (including zero-shot translation), text translation of dialogues, speech recognition and speech translation of lectures. Multilingual translation will target English, German, Dutch, Italian and Romanian; translations of dialogues will be from Japanese to English; and speech translation of lectures will be from German to English. Additional unofficial text translations of TED talks will be offered à-la-carte according to expressions of interest by the participants. Training and development data will be released to the participants through the workshop website. For the multilingual task both large and small training data constraints will be defined.
Scientific Papers
The IWSLT invites submissions of scientific papers to be published in the workshop proceedings and presented in dedicated technical sessions of the workshop, either in oral or poster form. The workshop welcomes high quality, original contributions covering theoretical and practical issues in the fields of automatic speech recognition and machine translation that are applied to spoken language translation. Possible topics include, but are not limited to:
MT and SLT approaches
Integration of ASR and MT
MT and SLT evaluation
Language resources for MT and SLT
Open source software for ASR, MT and SLT
Multilingual MT and ASR
Applications of MT and SLT
Adaptation in MT, ASR and SLT
Post- and Pre-processing for ASR, MT and SLT
Efficiency in ASR, MT and SLT
IMPORTANT DATES
Evaluation Campaign
June 5: Release of train and dev data (*)
Sep. 11 - 17: Multilingual task evaluation
Sep. 11 - 17: Lectures ASR evaluation
Sep. 18 - 24: Lectures SLT evaluation
Sep. 18 - 24: Dialogue task evaluation
Oct. 22: System description paper
Nov. 12: Review feedback
Nov. 26: Camera ready
(*) Release of training data of the Dialogue task will be announced later.
Scientific Papers
Sep. 30: Paper submissions
Oct. 31: Notification of acceptance
Nov. 12: Camera ready
Submitted manuscripts will be subject to a blind peer-reviewed. Authors of accepted papers are requested to present their paper at the workshop.