|26 March 2020 New||Deadline extension! The new submission deadline is 09 April 2020. Please check the dedicated "Important Dates" section.|
|24 March 2020||More information about reproducibility are online. Please check the dedicated "Evaluation Process" section in the task page for details.|
|09 March 2020||If you want to check how the evaluation system works (e.g., in case you have not formed a team yet) you can submit an anonymous solution (team name only with anonymous members). For more info, please refer to this post in the Google Group.|
|02 March 2020||The submissions evaluation is now updated as a consequence of the release of the Large labelled dataset. Please check the leaderboard page for details.|
|01 March 2020||Large labelled dataset is available! Please check the dedicated "Datasets" section in the task page.|
|20 February 2020||Megagon and Microsoft are sponsors of the contest!|
|19 February 2020||First 6 registered teams are in the leaderboard!|
|17 February 2020||Team registration and solution submission are open! Please check the dedicated "Submitting" section in the task page.|
|07 February 2020||Dataset is available!|
|23 January 2020||The new contest page is up!|
Student teams from degree-granting institutions are invited to compete in the annual SIGMOD Programming Contest. This year, the subject of the contest is to construct an Entity Resolution system. Teams' submissions will be judged on their overall performance on a supplied dataset.
The winning team will be awarded a prize of USD $7,000, and there will be an additional prize of USD $3,000 for the runner-up. One member of each of the top 5 teams will receive a travel grant to attend SIGMOD 2020 in Portland, Oregon.
For this year's contest, the task is Entity Resolution. Entity Resolution is the problem of identifying and matching different manifestations of the same real-world object in a dataset. Ironically, Entity Resolution has many duplicate names in the literature, including Record Linkage, Deduplication, Approximate Match, Entity Clustering, and so on.
For this task you need to identify which product specifications (in short, specs) from multiple e-commerce websites represent the same real-world product. All specs refer to cameras and include information about the camera model (e.g. Canon EOS 5D Mark II) and, possibly, accessories (e.g. lens kit, bag, tripod). The challenge is to develop an Entity Resolution system for matching the specs with the same camera models with high precision and recall.
More details about this year's problem can be found on the task page.
|23 January 2020||Contest requirements specification available.|
|07 February 2020||Dataset available.|
|17 February 2020||Team registration begins. Leaderboard available.|
|Final submission deadline.New|