Corpus ID: 7712273

Semantic Role Labeling for Open Information Extraction

@inproceedings{Christensen2010SemanticRL,
  title={Semantic Role Labeling for Open Information Extraction},
  author={J. Christensen and Mausam and S. Soderland and Oren Etzioni},
  booktitle={HLT-NAACL 2010},
  year={2010}
}
Open Information Extraction is a recent paradigm for machine reading from arbitrary text. In contrast to existing techniques, which have used only shallow syntactic features, we investigate the use of semantic features (semantic roles) for the task of Open IE. We compare TextRunner (Banko et al., 2007), a state of the art open extractor, with our novel extractor SRL-IE, which is based on UIUC's SRL system (Punyakanok et al., 2008). We find that SRL-IE is robust to noisy heterogeneous Web data… Expand
80 Citations
Identifying Relations for Open Information Extraction
  • 1,151
  • PDF
Nested Propositions in Open Information Extraction
  • 37
  • PDF
ClausIE: clause-based open information extraction
  • 396
  • Highly Influenced
  • PDF
StuffIE: Semantic Tagging of Unlabeled Facets Using Fine-Grained Information Extraction
  • 9
  • PDF
Vietnamese Semantic Role Labelling
  • 2
  • PDF
GerIE - An Open Information Extraction System for the German Language
  • 8
  • PDF
A Distant Supervision Approach to Semantic Role Labeling
  • 12
  • PDF
Neural Open Information Extraction
  • 50
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 22 REFERENCES
Open Information Extraction from the Web
  • 2,136
  • PDF
The Tradeoffs Between Open and Traditional Relation Extraction
  • 400
  • PDF
A Probabilistic Model of Redundancy in Information Extraction
  • 218
  • PDF
Tree Kernels for Semantic Role Labeling
  • 172
  • PDF
Learning Information Extraction Rules for Semi-Structured and Free Text
  • 1,060
  • PDF
The Effect of Syntactic Representation on Semantic Role Labeling
  • 81
  • PDF
The Importance of Syntactic Parsing and Inference in Semantic Role Labeling
  • 400
  • Highly Influential
  • PDF
Snowball: extracting relations from large plain-text collections
  • 1,300
  • PDF
...
1
2
3
...