Identifying Relations for Open Information Extraction

@inproceedings{Fader2011IdentifyingRF,
  title={Identifying Relations for Open Information Extraction},
  author={Anthony Fader and Stephen Soderland and Oren Etzioni},
  booktitle={EMNLP},
  year={2011}
}
Open Information Extraction (IE) is the task of extracting assertions from massive corpora without requiring a pre-specified vocabulary. This paper shows that the output of state-of-the-art Open IE systems is rife with uninformative and incoherent extractions. To overcome these problems, we introduce two simple syntactic and lexical constraints on binary relations expressed by verbs. We implemented the constraints in the ReVerb Open IE system, which more than doubles the area under the… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 812 CITATIONS

Supervised Neural Models Revitalize the Open Relation Extraction

Shengbin Jia, Yang Xiang, Xiaojun Chen
  • ArXiv
  • 2018
VIEW 19 EXCERPTS
HIGHLY INFLUENCED

A Survey on Open Information Extraction

VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Detection of new drug indications from electronic medical records

  • 2016 IEEE RIVF International Conference on Computing & Communication Technologies, Research, Innovation, and Vision for the Future (RIVF)
  • 2016
VIEW 10 EXCERPTS
HIGHLY INFLUENCED

Health Web Science

  • Health Information Science
  • 2015
VIEW 11 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

INFORMATIVENESS MEASURE FOR ONLINE NEWS

FACTUAL DENSITY, AN As, Filipo Sharevski
  • 2015
VIEW 9 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2010
2019

CITATION STATISTICS

  • 178 Highly Influenced Citations

  • Averaged 94 Citations per year from 2017 through 2019