Northeastern University Runs at the TREC12 Crowdsourcing Track

Abstract

The goal of the TREC 2012 Crowdsourcing Track was to evaluate approaches to crowdsourcing high quality relevance judgments for images and text documents. This paper describes our submission to the Text Relevance Assessing Task. We explored three different approaches for obtaining relevance judgments. Our first two approaches are based on collecting a limited number of preference judgments from Amazon Mechanical Turk workers. These preferences are then extended to relevance judgments through the use of expectation maximization and the Elo rating system. Our third approach is based on our Nugget-based evaluation paradigm.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Feb 06, 2013
Accession Number
ADA581299

Entities

People

  • Javed A. Aslam
  • Jesse Anderton
  • Jie Wu
  • Maryam Bashir
  • Matthew Ekstrand-abueg
  • Peter B. Golbus
  • Virgil Pavlu

Organizations

  • Northeastern University

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Algorithms
  • Computers
  • Crowdsourcing
  • Experimental Design
  • Extraction
  • Human Intelligence
  • Information Operations
  • Information Science
  • Instructions
  • Judgment
  • Neurobehavioral Manifestations
  • Probability
  • Probability Distributions
  • Ratings
  • Standards
  • Test And Evaluation
  • Universities

Fields of Study

  • Computer science

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Information Retrieval
  • Instructional Design and Training Evaluation.