Go to the NIST home page Go to the TAC Home Page TAC Banner

Return to TAC Homepage

TAC 2014 Tracks
  KBP Tracks
      Cold Start
      Entity Linking
      Slot Filling (SF)
      SF Validation
      Sentiment
      Event
    Data
    Schedule
    Organizers
    Call for Participation
    Track Registration
  BiomedSumm Track
Reporting Guidelines
TAC 2014 Workshop




Knowledge Base Population (KBP) 2014

Evaluation: February-November, 2014
Workshop: November 17-18, 2014

Follow us on twitter @tackbp

Conducted by:
U.S. National Institute of Standards and Technology (NIST)

With support from:
U.S. Department of Defense

Overview

The goal of TAC Knowledge Base Population (KBP) is to develop and evaluate technologies for building and populating knowledge bases (KBs) from unstructured text. KBP systems must ultimately build a KB from scratch, but must also be able to populate an existing reference KB that has incomplete or unkown provenance.

The task of Cold Start is to build a KB from scratch, using a predefined KB schema and a collection of unstructured text. The current KB schema consists of named entities that can be a person (PER), organization (ORG), or geopolitical entity (GPE); and predefined attributes (a.k.a "slots") for those named entities.

Cold Start KBP can be decomposed into two complementary tasks: entity linking, in which entity mentions must be linked to entities in a reference KB or new entities discovered in the document collection; and slot filling, which involves finding predefined attributes about target entities in unstructured text. The reference KB for 2014 is based on a snapshot of English Wikipedia from October 2008 and is the same reference KB that has been used in TAC KBP since 2009. Each node in the reference KB corresponds to a Wikipedia page for a person, organization, or geopolitical entity and consists of predefined attributes derived from Wikipedia infoboxes. Unstructured text from the Wikipedia page is also available (as "wiki_text") in the reference KB.

The event and sentiment tracks in KBP 2014 aim to extract information about events and sentiment from unstructured text, such that the information would be suitable as input into a structured KB.

Finally, the slot filler validation track focuses on the refinement of output from slot filling systems by either combining information from multiple slot filling systems, or applying more intensive linguistic processing to validate candidate slot fillers.

Tracks

  • Cold Start KBP
    The Cold Start track builds a knowledge base from scratch.
    Track coordinator: James Mayfield (jamesmayfield@gmail.com)
    Track home page: http://tac.nist.gov/2014/KBP/ColdStart/

  • Entity Linking
    The entity linking task is to discover and link names in a document collection to entities in a reference KB, or to new named entities discovered in the document collection.
    Track coordinator: Heng Ji (jih@rpi.edu)
    Track home page: http://nlp.cs.rpi.edu/kbp/2014/

  • Slot Filling
    The slot filling task is to search a document collection to fill in values for predefined slots (attributes) for a given entity in a reference KB.
    Track coordinator: Mihai Surdeanu (msurdeanu@email.arizona.edu)
    Track home page: http://surdeanu.info/kbp2014/index.php

  • Slot Filler Validation
    The Slot Filler Validation track focuses on the refinement of output from slot filling systems by either combining information from multiple slot filling systems, or applying more intensive linguistic processing to validate individual candidate slot fillers.
    Track coordinator: Hoa Dang (hoa.dang@nist.gov) and Yasaman Haghpanah (yasaman.haghpanah@nist.gov)
    Track home page: http://tac.nist.gov/2014/KBP/SFValidation/

  • Sentiment
    The goal of the Sentiment track is to assess the quality of detectors for scoped and attributed sentiment.
    Track coordinator: Claire Cardie (cardie@cs.cornell.edu)
    Track home page: http://tac.nist.gov/2014/KBP/Sentiment/

  • Event
    The goal of the Event track is to extract information about events such that the information would be suitable as input to a knowledge base.
    Track coordinator: Marjorie Freedman (mfreedma@bbn.com)
    Track home page: http://tac.nist.gov/2014/KBP/Event/

Preliminary Schedule

    TAC KBP 2014 Schedule
    MarchInitial track guidelines posted
    AprilDistribution of document collections
    June 15Deadline for registration for track participation
    July - SeptemberTrack evaluation windows (varies by track)
    October 7Deadline for short system descriptions
    October 7Deadline for workshop presentation proposals
    By OctoberRelease of individual evaluated results to participants (varies by track)
    mid OctoberNotification of acceptance of presentation proposals
    Nov 1 Nov 9Deadline for system reports (workshop notebook version)
    November 17-18TAC 2014 workshop in Gaithersburg, Maryland, USA
    February 15, 2015Deadline for system reports (final proceedings version)

Organizing Committee (Partial)

Claire Cardie (Cornell University)
Hoa Trang Dang (U.S. National Institute of Standards and Techonology)
Jason Duncan (U.S. Department of Defense)
Joe Ellis (Linguistic Data Consortium)
Marjorie Freedman (BBN Technologies)
Kira Griffitt (Linguistic Data Consortium)
Ralph Grishman (New York University)
Yasaman Haghpanah (U.S. National Institute of Standards and Techonology)
Heng Ji (Rensselaer Polytechnic Institute)
James Mayfield (Johns Hopkins University)
Boyan Onyshkevych (U.S. Department of Defense)
Stephanie Strassel (Linguistic Data Consortium)
Mihai Surdeanu (University of Arizona)


NIST is an agency of the
U.S. Department of Commerce

privacy policy / security notice / accessibility statement
disclaimer
FOIA

Last updated: Tuesday, 28-Mar-2017 09:21:01 MDT
Comments to: tac-web@nist.gov