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

Return to TAC Homepage

TAC 2017 Tracks
  KBP Tracks
  ADR Track
Call for Participation
Track Registration
Reporting Guidelines
TAC 2017 Workshop




Text Analysis Conference (TAC) 2017

Evaluation: February-November, 2017
Workshop: November 13-14, 2017

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

With support from:
U.S. Department of Defense

The Text Analysis Conference (TAC) is a series of evaluation workshops organized to encourage research in Natural Language Processing and related applications, by providing a large test collection, common evaluation procedures, and a forum for organizations to share their results. TAC comprises sets of tasks known as "tracks," each of which focuses on a particular subproblem of NLP. TAC tracks focus on end-user tasks, but also include component evaluations situated within the context of end-user tasks.

TAC 2017 has six tracks in two major areas:

  • Adverse Drug Reaction Extraction from Drug Labels (ADR)
    The purpose of this track is to test various natural language approaches for their information extraction performance on adverse drug reactions (ADR). Participants will be provided with mention-, relation-, and document-level annotations in order to extract structured ADR information from the Food and Drug Administration's (FDA) official pharmaceutical knowledge base.
    Track coordinator: Kirk Roberts (Kirk.Roberts@uth.tmc.edu)
    Home page: https://bionlp.nlm.nih.gov/tac2017adversereactions/
    Mailing list: tac-adr@googlegroups.com

  • Knowledge Base Population (KBP)
    KBP tracks develop technologies for building and populating knowledge bases (KBs) from unstructured text. In addition to the main end-to-end KB construction task in the Cold Start KB track, component tasks are offered in 4 tracks that focus on specific components of the KB:
    • Cold Start KB (CSKB): The Cold Start KB track builds a knowledge base from scratch using a given document collection and knowledge base schema. The KB schema includes entities, events, and relations involving entities and events, including entity attributes (aka slots), event arguments, and sentiment between entities.
    • Entity Discovery and Linking (EDL): The Entity Discovery and Linking track aims to extract entity mentions from a source collection of textual documents and link them to a reference KB; an EDL system is also required to cluster mentions for those entities that don't have corresponding KB entries.
    • Slot Filling (SF): The Slot Filling task is to search a document collection to fill in values for predefined slots (attributes) for a given entity.
    • 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. The track includes Event Nugget (EN) tasks to detect and link events, and Event Argument (EAL) tasks to extract event arguments and link arguments that belong to the same event.
    • Belief and Sentiment (BeSt): The Belief and Sentiment track detects belief and sentiment of an entity toward another entity, relation, or event.
    Home page: tac.nist.gov/2017/KBP/
    Mailing list: tac-kbp@nist.gov

    TAC 2017 Schedule
    February 20Track registration opens
    June 15Deadline for registration for track participation
    June - OctoberTrack evaluation windows (varies by track)
    By mid OctoberRelease of individual evaluated results to participants (most tracks)
    October 15Deadline for short system descriptions
    October 15Deadline for workshop presentation proposals
    October 20Notification of acceptance of presentation proposals
    November 1Deadline for system reports (workshop notebook version)
    November 13-14TAC 2017 workshop in Gaithersburg, Maryland, USA
    February 28, 2018Deadline for system reports (final proceedings version)


BACK to General Information about Tracks

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

privacy policy / security notice / accessibility statement
disclaimer
FOIA

Last updated: Wednesday, 14-Feb-2018 10:13:47 EST
Comments to: tac-web@nist.gov