Overview of the IWSLT 2009 evaluation campaign

Michael Paul


Abstract
This paper gives an overview of the evaluation campaign results of the International1Workshop on Spoken Language Translation (IWSLT) 2009 . In this workshop, we focused on the translation of task-oriented human dialogs in travel situations. The speech data was recorded through human interpreters, where native speakers of different languages were asked to complete certain travel-related tasks like hotel reservations using their mother tongue. The translation of the freely-uttered conversation was carried out by human interpreters. The obtained speech data was annotated with dialog and speaker information. The translation directions were English into Chinese and vice versa for the Challenge Task, and Arabic, Chinese, and Turkish, which is a new edition, into English for the standard BTEC Task. In total, 18 research groups participated in this year’s event. Automatic and subjective evaluations were carried out in order to investigate the impact of task-oriented human dialogs on automatic speech recognition (ASR) and machine translation (MT) system performance, as well as the robustness of state-of-the-art MT systems for speech-to-speech translation in a dialog scenario.
Anthology ID:
2009.iwslt-evaluation.1
Volume:
Proceedings of the 6th International Workshop on Spoken Language Translation: Evaluation Campaign
Month:
December 1-2
Year:
2009
Address:
Tokyo, Japan
Venue:
IWSLT
SIG:
Publisher:
Note:
Pages:
1–18
Language:
URL:
https://aclanthology.org/2009.iwslt-evaluation.1
DOI:
Bibkey:
Cite (ACL):
Michael Paul. 2009. Overview of the IWSLT 2009 evaluation campaign. In Proceedings of the 6th International Workshop on Spoken Language Translation: Evaluation Campaign, pages 1–18, Tokyo, Japan.
Cite (Informal):
Overview of the IWSLT 2009 evaluation campaign (Paul, IWSLT 2009)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/2009.iwslt-evaluation.1.pdf
Presentation:
 2009.iwslt-evaluation.1.Presentation.pdf