ASR Task
Each participant has to submit at least one run for each recognition task s/he registered for.
Multiple run submissions are allowed, but participants must explicitly indicate one PRIMARY run for each track. All other run submissions are treated as CONTRASTIVE runs. In case that none of the runs is marked as PRIMARY, the latest submission (according to the file time-stamp) for the respective track will be used as the PRIMARY run.
Runs have to be submitted as a gzipped TAR archive (format see below) and sent as an email attachment to sebastian stueker ∂does-not-exist.kit edu and cettolo AT fbk.eu.
Submissions have to be made in CTM format. See the ctm documentation in the NIST SCTK documentation for details. The confidence values are optional. The channel number has to be '1'. Submissions have to be in UTF-8.
This year, no pre-defined segmentation is given for the ASR task. Instead an unsegmented uem file will be provided with the evaluation data. Automatic segmentation of the data is mandatory for this year's ASR track.
Output conventions:
- The text will be scored case-insensitive, but can be submitted case-sensitive
- Numbers, dates etc. need to be transcribed in words as they are spoken, not in digits
- Common acronyms such as NATO, EU, are written as one word, without any special markers between the letters. This applies no matter whether they are spoken as one word or spelled out as a letter sequence
- All other letter spelling sequences are written as individual letters with space inbetween
- Standard abbreviations, such as "etc." "Mr." are accepted and will be added to the glm file in the scoring package
- For words pronounced in their contracted form, the orthography for the contracted form may be used. These cases will be normalized by the glm file to their canonical form.
TAR archive file structure:
< UserID >/< Set >.< Task >.< UserID >.primary.ctm
/< Set >.< Task >.< UserID >.contrastive1.ctm
/< Set >.< Task >.< UserID >.contrastive2.ctm
/...
where:
< UserID > = user ID of participant used to download data files
< Set > = dev2010 | tst2010 | dev2012 | tst2013
< Task > = ASR_<LID>
< LID > = DE | EN
Examples:
fbk/dev2010.ASR_E.fbk.primary.ctm
/dev2010.ASR_SC_E.fbk.primary.ctm
/dev2010.ASR_SC_E.fbk.contrastive1.ctm
Re-submitting your runs is allowed as far as the mails arrive BEFORE the submission deadline. In case that multiple TAR archives are submitted by the same participant, only runs of the most recent submission mail will be used for the IWSLT 2012 evaluation and previous mails will be ignored.
MT and SLT Tasks
Each participant has to submit at least one run for each of the translation task s/he registered for.
Multiple run submissions are allowed, but participants must explicitly indicate one PRIMARY run for each track. All other run submissions are treated as CONTRASTIVE runs. In case that none of the runs is marked as PRIMARY, the latest submission (according to the file time-stamp) for the respective track will be used as the PRIMARY run.
Runs have to be submitted as a gzipped TAR archive (format see below) and e-mailed to sebastian stueker ∂does-not-exist.kit edu and cettolo AT fbk.eu.
TAR archive file structure:
<UserID>/<Set>.<Task>.<UserID>.primary.xml
/<Set>.<Task>.<UserID>.contrastive1.xml
/<Set>.<Task>.<UserID>.contrastive2.xml
/...
where:
<UserID> = user ID of participant used to download data files
<Set> = dev2010 | tst2010 | dev2011 | tst2013
<Task> = SLT_<fromLID><toLID> | MT_<fromLID><toLID>
<fromLID>, <toLID> = Language identifiers (LIDs) as given by ISO 639-1 codes; see for example the WIT3 webpage.
Examples:
fbk/dev2010.SLT_EF.fbk.primary.xml
/dev2010.SLT_EF.fbk.contrastive1.xml
/dev2010.SLT_EF.fbk.contrastive2.xml
/tst2010.MT_SC_EF.fbk.primary.xml
/tst2010.MT_CE.fbk.primary.xml
Re-submitting your runs is allowed as far as the mails arrive BEFORE the submission deadline. In case that multiple TAR archives are submitted by the same participant, only runs of the most recent submission mail will be used for the IWSLT 2013 evaluation and previous mails will be ignored.
