WIT3

Web Inventory of Transcribed and Translated Talks

Home 2014-01-test Evaluation sets for the MT track

The IWSLT 2014 Evaluation Campaign includes the MT trackon TED Talks. In this edition, the official language pairs are five:

   from English to French
   from English to German
   from German to English
   from English to Italian
   from Italian to English

Optional tasks are proposed with English paired in both directions with other twelve languages:

   from/to English to/from Arabic, Spanish, Farsi, Hebrew, Dutch, Polish, Portuguese-Brazil, Romanian, Russian, Slovenian, Turkish and Chinese

Linguistic preprocessors for normalize/cleaning Arabic, Farsi and Hebrew texts are available here; they were used for the development and the scoring of baseline systems and will be employed for the official evaluation of submissions.

Submitted runs on optional pairs will be evaluated as well, in the hope to stimulate the MT community to evaluate systems on common benchmarks and to share achievements on challenging translation tasks.

For each language pair, test sets are linked to the corresponding entry of the table below: by clicking, an archive will be downloaded which contains the sets and a README file.

If you use this corpus in your work, please cite the paper:

M. Cettolo, C. Girardi, and M. Federico. 2012. WIT3: Web Inventory of Transcribed and Translated Talks. In Proc. of EAMT, pp. 261-268, Trento, Italy. pdf, bib.


ar

de

en

es

fa

fr

he

it

nl

pl

pt-br

ro

ru

sl

tr

zh
ar  click to get
test sets
             
de  click to get
test sets
             
enclick to get
test sets
click to get
test sets
 click to get
test sets
click to get
test sets
click to get
test sets
click to get
test sets
click to get
test sets
click to get
test sets
click to get
test sets
click to get
test sets
click to get
test sets
click to get
test sets
click to get
test sets
click to get
test sets
click to get
test sets
es  click to get
test sets
             
fa  click to get
test sets
             
he  click to get
test sets
             
it  click to get
test sets
             
nl  click to get
test sets
             
pl  click to get
test sets
             
pt-br  click to get
test sets
             
ro  click to get
test sets
             
ru  click to get
test sets
             
sl  click to get
test sets
             
tr  click to get
test sets
             
zh  click to get
test sets