The paper overviews the tenth evaluation campaign orga- nized by the IWSLT workshop. The 2013 evaluation offered multiple tracks on lecture transcription and translation based on the TED Talks corpus. In particular, this year IWSLT included two automatic speech recognition tracks, on En- glish and German, three speech translation tracks, from En- glish to French, English to German, and German to English, and three text translation track, also from English to French, English to German, and German to English. In addition to the official tracks, speech and text translation optional tracks were offered involving 12 other languages: Arabic, Spanish, Portuguese (B), Italian, Chinese, Polish, Persian, Slovenian, Turkish, Dutch, Romanian, Russian. Overall, 18 teams par- ticipated in the evaluation for a total of 217 primary runs sub- mitted. All runs were evaluated with objective metrics on a current test set and two progress test sets, in order to compare the progresses against systems of the previous years. In ad- dition, submissions of one of the official machine translation tracks were also evaluated with human post-editing.
Report on the 10th IWSLT Evaluation Campaign,
Cettolo, Mauro;Bentivogli, Luisa;Federico, Marcello
2013-01-01
Abstract
The paper overviews the tenth evaluation campaign orga- nized by the IWSLT workshop. The 2013 evaluation offered multiple tracks on lecture transcription and translation based on the TED Talks corpus. In particular, this year IWSLT included two automatic speech recognition tracks, on En- glish and German, three speech translation tracks, from En- glish to French, English to German, and German to English, and three text translation track, also from English to French, English to German, and German to English. In addition to the official tracks, speech and text translation optional tracks were offered involving 12 other languages: Arabic, Spanish, Portuguese (B), Italian, Chinese, Polish, Persian, Slovenian, Turkish, Dutch, Romanian, Russian. Overall, 18 teams par- ticipated in the evaluation for a total of 217 primary runs sub- mitted. All runs were evaluated with objective metrics on a current test set and two progress test sets, in order to compare the progresses against systems of the previous years. In ad- dition, submissions of one of the official machine translation tracks were also evaluated with human post-editing.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
