TAC KBP 2013 Cold Start Track

Overview

The Cold Start track combines entity linking and slot filling to populate an empty knowledge base using a predefined schema for the facts and relations that will compose the KB. The Cold Start schema is specified by the TAC KBP English slot filling task and consists of 3 entity types (PER, ORG, GPE) and binary relation types corresponding to the slots in the English slot filling track, plus inverse slots.

Given a collection of documents, the Cold Start system must find all PER, ORG, and GPE entities mentioned by name in the collection, create a KB node for each entity, and link each name mention to the correct entity node in the KB. All Cold Start relations that are attested in the document collection must be included in the KB, along with a confidence value and provenance consisting of a document and offsets for the subject, predicate, and object of the relation. For relations whose objects are themselves Cold Start entities (such as per:siblings or org:subsidiaries), systems must link to the KB node representing the correct entity; relations whose objects are strings (such as per:title or org:website) will use strings to represent the object. If a KB includes multiple instances of the same subject-predicate-object triple (but with different provenance information), the triple with the highest confidence value will be evaluated, and additional triples with confidence lower value may be evaluated as resources permit.

A Cold Start evaluation query consists of a named entity mention in the document collection (an "entry point"), and a sequence of one or more relation types. The entry point selects a single corresponding entity node in the KB, and the sequence of relation types is followed to arrive at a set of terminal slot fillers at the end of the sequence. The terminal slot fillers are then assessed and scored as in the English slot filling task. For example, a typical Cold Start query may ask "What are the ages of the siblings of the Bart Simpson mentioned in Document 42?" or "What schools are attended by the children of the Marge Simpson mentioned in Document 9?" Such "one-hop" queries will verify that the knowledge base is well-formed in a way that goes beyond basic entity linking and slot filling. In contrast to the Cold Start task in KBP 2012, each Cold Start evaluation query in 2013 will have multiple entry points (i.e., multiple mentions of the same entity), in order to mitigate cascaded errors caused by submitted KBs that are not able to link every name mention to a KB entity node.

In addition to testing systems' ability to combine entity-linking and slot-filling, a major goal of Cold Start is to see how well systems can perform these tasks when no structured knowledge exists for most of the entities participating in CS relations. The Cold Start corpus will consist of tens of thousands of news and Web documents drawn from the TREC Knowledge Base Acceleration corpus, that contain relations about entities that are not included in existing well-known knowledge bases. Because the task can begin as soon as the document collection is available, the collection will not be distributed until the start of the task evaluation window.

Schedule

April	Track guidelines posted
By early June	Distribution of document collections
June 15	Deadline for registration for track participation
August 6-26	Extended Cold Start evaluation window
By late September	Release of individual evaluated results to participants
September 30	Deadline for short system descriptions
September 30	Deadline for workshop presentation proposals
mid October	Notification of acceptance of presentation proposals
November 8	Deadline for system reports (workshop notebook version)
November 18-19	TAC KBP 2013 workshop in Gaithersburg, Maryland, USA
February 15, 2014	Deadline for system reports (final proceedings version)

Track Coordinator