Corpus ID: 9400086

Bootstrapping Distantly Supervised IE Using Joint Learning and Small Well-Structured Corpora

@inproceedings{Bing2017BootstrappingDS,
  title={Bootstrapping Distantly Supervised IE Using Joint Learning and Small Well-Structured Corpora},
  author={Lidong Bing and Bhuwan Dhingra and Kathryn Mazaitis and Jong Hyuk Park and William W. Cohen},
  booktitle={AAAI},
  year={2017}
}
We propose a framework to improve performance of distantly-supervised relation extraction, by jointly learning to solve two related tasks: concept-instance extraction and relation extraction. We combine this with a novel use of document structure: in some small, well-structured corpora, sections can be identified that correspond to relation arguments, and distantly-labeled examples from such sections tend to have good precision. Using these as seeds we extract additional relation examples by… Expand
Tackling Long-Tailed Relations and Uncommon Entities in Knowledge Graph Completion
Semi-Supervised Learning with Declaratively Specified Entropy Constraints

References

SHOWING 1-10 OF 23 REFERENCES
Distant IE by Bootstrapping Using Lists and Document Structure
Multi-instance Multi-label Learning for Relation Extraction
Distant supervision for relation extraction without labeled data
Modeling Relations and Their Mentions without Labeled Text
Learning to Extract Relations from the Web using Minimal Supervision
Improving Distant Supervision for Information Extraction Using Label Propagation Through Lists
Open Information Extraction Using Wikipedia
Dependency Parsing and Domain Adaptation with LR Models and Parser Ensembles
Snowball: extracting relations from large plain-text collections
...
1
2
3
...