The official shared task on Quality Estimation aims to further examine automatic methods for estimating the quality of neural machine translation output at run-time, without relying on reference translations. As in previous years, we cover estimation at various levels. Important elements introduced this year include: a new task where sentences are annotated with Direct Assessment (DA) scores instead of labels based on post-editing; a new multilingual sentence-level dataset mainly from Wikipedia articles, where the source articles can be retrieved for document-wide context; the availability of NMT models to explore system-internal information for the task.
In addition to generally advancing the state of the art at all prediction levels for modern neural MT, our specific goals are:
Offical task webpage: QE Shared Task 2020
This submission platform covers Task 2: Word-level *Post-Editing Effort*.
In Task 2, participating systems are required to detect errors both on source side (to detect which words caused errors) and target side (to detect mistranslated or missing words):
Submission Format
The output for the word-level subtask can be up to two separate files: one with MT labels (for words and gaps) and another one with source words. You can submit for either of these subtasks or both of them, independently. The output format should be the same as in the .tags
and .source_tags
files in the training data; i.e., the .tags
file should be formatted as:
GAP_1 WORD_1 GAP_2 WORD_2 ... GAP_n WORD_n GAP_n+1
and the .source_tags
file should be:
WORD_1 WORD_2 ... WORD_n
Where each WORD_i
and GAP_i
is either OK or BAD. Tags must be delimited by whitespace or a tab character.
For MT labels, each sentence will therefore correspond to 2n+1 tags (where n is the number of words in the sentence), alterating gaps and words, in order. For source labels, each sentence will correspond to n tags.
For example, consider the following MT document and its post edited version. The wrong words are highlighted:
anschließend wird in jeder Methode die übergeordnete Superclass-Version von selbst aufgerufen .
anschließend wird in jeder Methode die Superclass-Version dieser Methode aufgerufen .
For this translation, output tags should be as follows. To make them easier to distinguish, tags referring to gaps are highlighted in yellow, while those referring to words are in blue. In this example, all BAD words can be either removed or replaced by other words in the post edited text; since no insertions are necessary, all gaps are tagged as OK.
OK OK OK OK OK OK OK OK OK OK OK OK OK BAD OK OK OK BAD OK BAD OK OK OK OK OK
To allow the automatic evaluation of your predictions, please submit them in a file named as follows:
and package them in a single zipped file (.zip).
If you don't have predictions for either one of the sub-tasks, only include what you have in your submission. If one of the files is missing, the scoring program will simply assign the score of 0 to the missing predictions.
Submissions will be evaluated in terms of MCC (Matthews correlation coefficient).
The data is publicly available but since it has been provided by our industry partners it is subject to specific terms and conditions. However, these have no practical implications on the use of this data for research purposes.
Participants are allowed to explore any additional data and resources deemed relevant.
The provided QE labelled data is publicly available under Creative Commons Attribution Share Alike 4.0 International (https://github.com/facebookresearch/mlqe/blob/master/LICENSE).
Each participating team can submit at most 30 systems for each of the language pairs of each subtask (max 5 a day).
Start: April 19, 2020, midnight
Start: April 19, 2020, midnight
Never
You must be logged in to participate in competitions.
Sign In