Overview of the TREC 2014 Contextual Suggestion Track

Abstract

The contextual suggestion track investigates search techniques for complex information needs that are highly dependent on context and user interests. For example, imagine an information retrieval researcher with a November evening to spend in Gaithersburg, Maryland. A contextual suggestion system might recommend a beer at the Dogfish Head Alehouse, dinner at the Flaming Pit, or even a trip into Washington on the metro to see the National Mall. The primary goal of this track is to develop evaluation methodologies for such systems. This track ran for the third time as part of TREC 2014 after a positive response in previous years. This year participants were again given, as input, a set of profiles and set of geographical contexts. The task was to take these profiles and contexts and to produce a list of up to 50 ranked suggestions for each profile-context pair. Participants could choose to gather suggestions from either the open web or the ClueWeb12 dataset.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Nov 01, 2014
Accession Number
ADA618816

Entities

People

  • Adriel Dean-hall
  • Charles L. Clarke
  • Ellen Voorhes
  • Jaap Kamps
  • Paul M. Thomas

Organizations

  • University of Waterloo

Tags

DTIC Thesaurus Topics

  • Abstracts
  • Algorithms
  • Commerce
  • Information Operations
  • Information Retrieval
  • Judgment
  • Language
  • Learning
  • Maryland
  • Probability
  • Ratings
  • Standards
  • United States
  • Universities
  • Vector Spaces
  • Web Service
  • Websites

Readers

  • Academic Conference Management
  • Educational Psychology
  • Information Retrieval

Technology Areas

  • AI & ML
  • AI & ML - Information Retrieval