How to Participate


  • January 2020             Data Release
  • June 30, 2020            Registration Deadline
  • July 31, 2020              Result Submission Deadline
  • August, 2020             Evaluation results will be reported to the participants
  • December 2020        Conference (NTCIR-15, Tokyo)
  • May 2020                    Proceedings will be published

    Just wanna peek: Willing to know if it’s interesting

    You can download only the training data for all 30 languages (Trial Datasets). You can feel what the data look like and understand the task. With the training data of a specific language, your task at full-participation is to categorize all the remaining Wikipedia entities of the language. 

    Procedure of Full-Participation

    1. Registration through NTCIR-15
    2. Account Creation and Data download
    3. Result Submission
    4. Conference (NTCIR-15)


    1.  Registration through NTCIR-15

    SHINRA2020-ML is one of the tasks at NTCIR-15. Please register through NTCIR-15 at the following site.

        NTCIR-15 Registration page

    2.  Account Creation and Data Download

    SHINRA2020-ML is a task to categorize 30 language Wikipedia entities into ENE  categories. (You can participate one or more language evaluation). You will need training data (already categorized Wikipedia data) and target data (the Wikipedia entities you will categorize). All those data can be downloaded from the following page: (Shinra2020-ml Data download page) In order to download it, you need to create your account at the following page (Shinra: Account Creation).

    3. Result Submission

    You need to submit the data through the specified page (TBA). The deadline of result submission is July 30, 2020.

    4.  Conference (NTCIR-15)

    The results can be presented at a conference (NTCIR-15). The detail will be announced.