The shared evaluation task of the workshop will examine automatic evaluation metrics for machine translation. We will provide all of the translations produced in the translation task and the system combination task, as well as the reference human translations. You will return rankings for each of the translations at the system-level and/or at the sentence-level. We will calculate the correlation of your rankings with the human judgements once the manual evaluation has been completed.

Goals

The goals of the shared evaluation task are:

• To achieve the strongest correlation with human judgments of translation quality
• To illustrate the suitability of an automatic evaluation metric as a surrogate for human evaluations
• To address the problems associated with comparing against a single reference translation
• To move automatic evaluation beyond system-level ranking to finer-grained sentence-level ranking

Task Description

We will provide the output of machine translation systems for five different language pairs (French-English, Spanish-English, German-English, Czech-English, Haitian Creole-English), and will give you the reference translations in each of those languages. You will provide scores for each of the outputs at the system-level and the sentence-level. If your automatic metric does not produce sentence-level scores, you can participate in just the system-level ranking. If your automatic metric uses linguistic annotation and cannot work with translations into languages other than English, you are free to assign scores only for translations into English.

We will measure the goodness of automatic evaluation metrics in the following ways:

• System-level correlation: We will use Spearman's rank correlation coefficient (rho) to measure the correlation of the automatic metrics with the human judgments of translation quality at the system-level. The human ranking of the systems will be based on the manual evaluation. A system's rank will be assigned based on the percent of time that the sentences it produced were judged to be better than or equal to the translations of any other system. Since automatic metrics generally assign a score rather than a rank, we will convert their raw scores into ranks prior to calculating rho.

• Sentence-level correlation: We will use Kendall's tau to measure metrics' correlation with human judgments at the sentence-level. For every pairwise comparison of two systems' output for a single sentence, we will count the automatic metric as being concordunt with the human judgment if it orders the systems' output the same way (i.e. the metric assigned a higher score to the higher ranked system). We will exclude pairs that the human annotators ranked as ties.

Submission Format

Once we receive the system outputs from the translation task and the system combination task we will post all of the system outputs for you to score with your metric. The translations will be distributed as plain text files with one translation per line. (We can also provide the output in the NIST MT Evaluation Workshop's XML format. Please contact us if this format is easier for you.)

The output of your software should produce scores for the translations either at the system-level or the segment-level (or preferably both).

Output file format for system-level rankings

The output files for system-level rankings should be formatted in the following way:

<METRIC NAME>   <LANG-PAIR>   <TEST SET>   <SYSTEM>   <SYSTEM LEVEL SCORE>

• METRIC NAME is the name of your automatic evaluation metric.
• LANG-PAIR is the language pair using two letter abbreviations for the languages (cz for Czech, de for German, en for English, es for Spanish, fr for French). You should use de-en for German-English, for example.
• TEST SET is the ID of the test set (given by the setid attribute of of the tstset tag in the XML file, or by the directory structure in the plain text files).
• SYSTEM is the ID of system being scored (given by the sysid attribute in the XML document, or as part of the filename for the plain text file).
• SYSTEM LEVEL SCORE is the overall system level score.

Output file format for segment-level rankings

The output files for segment-level rankings should be formatted in the following way:

<METRIC NAME>   <LANG-PAIR>   <TEST SET>   <SYSTEM>   <SEGMENT NUMBER>   <SEGMENT SCORE>

• METRIC NAME is the name of your automatic evaluation metric.
• LANG-PAIR is the language pair using two letter abbreviations for the languages.
• TEST SET is the ID of the test set.
• SYSTEM is the ID of system being scored.
• SEGMENT NUMBER is the line number starting from one of the plain text input files.
• SEGMENT SCORE is the score for the particular segment.

Past Years' Data

The system outputs and human judgments from the last three years' workshops is available for download from the following links:

• WMT08: http://www.statmt.org/wmt08/results.html
• WMT09: http://www.statmt.org/wmt09/results.html
• WMT10: http://www.statmt.org/wmt10/results.html

Last year's data contains all of the system's translations, the source documents and reference human translations and the human judgments of the translation quality.

Other Requirements

If you participate in the evaluation shared task, we ask you to commit about 8 hours of time to do the manual evaluation. The evaluation will be done with an online tool.

You are invited to submit a short paper (4 to 6 pages) describing your automatic evaluation metric. You are not required to submit a paper if you do not want to. If you don't, we ask that you give an appropriate reference describing your metric that we can cite in the overview paper.

IMPORTANT DATES

supported by the EuroMatrixPlus project
P7-IST-231720-STP
funded by the European Commission
under Framework Programme 7