Closed anoopkunchukuttan closed 6 months ago
WMT23 released QE datasets for 5 Indian languages in En to Indic direction. These are: en-mr, en-hi, en-gu, en-ta, en-te. The references are also available, so these can also be used for reference based metrics.
Details here: WMT23 QE Task Report Dataset
For Marathi, post-edits are also available as are word-level annotations error annotations are also available.
WMT23 released QE datasets for 5 Indian languages in En to Indic direction. These are: en-mr, en-hi, en-gu, en-ta, en-te. The references are also available, so these can also be used for reference based metrics.
Details here: WMT23 QE Task Report Dataset
For Marathi, post-edits are also available as are word-level annotations error annotations are also available.