Knowledge-based weak supervision for information extraction of overlapping relations

  • Authors:

  • Raphael Hoffmann;Congle Zhang;Xiao Ling;Luke Zettlemoyer;Daniel S. Weld

  • Affiliations:

  • University of Washington, Seattle, WA;University of Washington, Seattle, WA;University of Washington, Seattle, WA;University of Washington, Seattle, WA;University of Washington, Seattle, WA

  • Venue:
  • HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 1
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

Information extraction (IE) holds the promise of generating a large-scale knowledge base from the Web's natural language text. Knowledge-based weak supervision, using structured data to heuristically label a training corpus, works towards this goal by enabling the automated learning of a potentially unbounded number of relation extractors. Recently, researchers have developed multi-instance learning algorithms to combat the noisy training data that can come from heuristic labeling, but their models assume relations are disjoint --- for example they cannot extract the pair Founded(Jobs, Apple) and CEO-of(Jobs, Apple). This paper presents a novel approach for multi-instance learning with overlapping relations that combines a sentence-level extraction model with a simple, corpus-level component for aggregating the individual facts. We apply our model to learn extractors for NY Times text using weak supervision from Free-base. Experiments show that the approach runs quickly and yields surprising gains in accuracy, at both the aggregate and sentence level.