![[Main Page]](/GikiCLEF/images/logoGikiCLEF.png)
For assessment, the first thing to be created after all submissions have been received is an answer pool, in which different justifications for the same answer are considered as different answers.
This pooling mechanism handles differences between HTML and XML, that is, only one will remain in the pool, as well as automatically filters out those pages which are easy to discard as invalid answers (such as disambiguation pages).
Then, and in order to minimize the assessors' workload, the system automatically adds the information that some answers are correct and self-justified given the info already in the topic management system, as well as correct (but not justified).
From an assessor point of view, they are presented with a list of answers which they have to - either check the correctness through inspecting the pages and the justifications if existing - or just check the justifications because it is already known by the system that the answer is correct but not self justified Also, the assessor can add comments about interesting issues (incompatible information in different languages, Wikipedia link translations incorrect, etc.) which may have a bearing on the evaluation score
In order to make the system as flexible as possible, the same answers can be evaluated by different assessors, and then have a conflict-solving procedure if they do not agree.
After all answers in the pool have been classified, the evaluation program computes the evaluation measures, also taking into consideration the more complicated cases:
- correct answers but no justification in any language -- deemed incorrect
- answers which depend on the language (for cases in which different language Wikipedias have conflicting answers)