ALTA logo Language Technology Programming Competition 2016
Home
Task Description
Useful Information
Submission
 
 

2016 Shared Task Description

Basic Task Description

Web endpoints are used to collate and disambiguate information about entities, e.g. the following endpoint can be used to refer to Barack Obama:

https://en.wikipedia.org/wiki/Barack_Obama

Wikipedia has been used extensively for automated entity recognition and disambiguation. But many other endpoints exist for the same entity, e.g.:

http://www.nytimes.com/topic/person/barack-obama
https://twitter.com/BarackObama

The goal of this task is to determine whether two URLs refer to the same underlying entity. For example, the NY Times and Twitter URLs above are entity pages for the same person. However, the following pair are referring to different entities:

https://twitter.com/realDonaldTrump
https://www.instagram.com/ivankatrump

Evaluation

We will use Kaggle in Class to evaluate the systems.

Data Files and Submission

We will use Kaggle in Class for this year's competition (look for the ALTA 2016 Challenge). The data files and submission instructions will be provided in the competition website.

In order to access the Kaggle in Class pages, you need to register with this shared task.

Important Dates

Release of training data On registration
Deadline for submission of results over test data 17 Oct 2016
Notification of results 21 Oct 2016
Deadline for submission of system description poster 4 Nov 2016

 

© ALTA 2016. Competition Organisers.