A Probabilistic Model of Redundancy in Information Extraction

Abstract

Unsupervised Information Extraction (UIE) is the task of extracting knowledge from text without using hand-tagged training examples. A fundamental problem for both UIE and supervised IE is assessing the probability that extracted information is correct. In massive corpora such as the Web, the same extraction is found repeatedly in different documents. How does this redundancy impact the probability of correctness? This paper introduces a combinatorial balls-andurns model that computes the impact of sample size, redundancy, and corroboration from multiple distinct extraction rules on the probability that an extraction is correct. We describe methods for estimating the model's parameters in practice and demonstrate experimentally that for UIE the model's log likelihoods are 15 times better, on average, than those obtained by Pointwise Mutual Information (PMI) and the noisy-or model used in previous work. For supervised IE, the model's performance is comparable to that of Support Vector Machines, and Logistic Regression.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2006
Accession Number
ADA454763

Entities

People

  • Doug Downey
  • Oren Etzioni
  • Stephen Soderland

Organizations

  • University of Washington

Tags

Communities of Interest

  • Biomedical

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence Software
  • Automata Theory
  • Computational Science
  • Computations
  • Computer Languages
  • Computer Science
  • Extraction
  • Information Science
  • Models
  • Named Entity Recognition
  • Probabilistic Models
  • Probability
  • Redundancy
  • Repetition Rate
  • Supervised Machine Learning
  • Unsupervised Machine Learning

Fields of Study

  • Computer science

Readers

  • Computational Linguistics
  • Regression Analysis.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Information Retrieval