Contents

Description
Important Dates
Datasets
Evaluation
Rules
Organizers

PASCAL Ontology Learning Challenge

This challenge is funded and organized in cooperation with the PASCAL network. Participation is open to all.

Description

The aim of this challenge is to encourage work on automated construction and population of ontologies. For the purposes of this challenge, an ontology consists of a set of concepts and a set of instances. An instance can be assigned to one or more concepts. The concepts are connected into a hierarchy.

Several types of tasks are included in this challenge:

Evaluation is based on comparing the results to a "golden standard" ontology prepared by human editors.

For more details, see the detailed task description (includes information about evaluation measures).

Important Dates

[Preliminary.]

February 10, 2006: Release of the datasets.

April 2, 2006: Deadline for end of the first round. Only submissions for tasks 1.1, 1.2, and 2.1 will be evaluated.

April 12, 2006: PASCAL Challenges Workshop: review of preliminary results from the first round, start of second round.
Participation in the second round is open to everyone, including those who have not participated in the first round.

December 1, 2006: End of the second round.

Datasets

Part 1: DMOZ Dataset

Part 2: Lonely Planet Dataset

On-line Evaluation Service

A form for the submission of final results will be provided later.

Rules

Anyone is allowed to participate. A participant may be either a single person or a group. A single person can participate in at most two groups. A participant is allowed to submit at most one solution for each task. However, it is not necessary to submit solutions for all tasks. Evaluation and ranking will be performed separately for each task.

Organizing Committee

Contact person: Marko Grobelnik.

Organizing committee: