Unsupervised Open Relation Extraction

@inproceedings{ElSahar2017UnsupervisedOR,
  title={Unsupervised Open Relation Extraction},
  author={Hady ElSahar and E. Demidova and S. Gottschalk and C. Gravier and F. Laforest},
  booktitle={ESWC},
  year={2017}
}
  • Hady ElSahar, E. Demidova, +2 authors F. Laforest
  • Published in ESWC 2017
  • Computer Science
  • We explore methods to extract relations between named entities from free text in an unsupervised setting. In addition to standard feature extraction, we develop a novel method to re-weight word embeddings. We alleviate the problem of features sparsity using an individual feature reduction. Our approach exhibits a significant improvement by \(5.8\%\) over the state-of-the-art relation clustering scoring a F1-score of 0.416 on the NYT-FB dataset. 
    15 Citations

    Figures, Tables, and Topics from this paper.

    Open Relation Extraction: Relational Knowledge Transfer from Supervised Data to Unsupervised Data
    • 9
    • Highly Influenced
    • PDF
    Language-consistent Open Relation Extraction: from Multilingual Text Corpora
    Clustering-based Unsupervised Generative Relation Extraction
    Knowledge Graph Generation with Deep Active Learning
    Neural Snowball for Few-Shot Relation Learning
    • 9
    • PDF
    Quantifying Similarity between Relations with Fact Distribution
    • 2
    • PDF
    Unsupervised Approaches for Textual Semantic Annotation, A Survey
    • 24
    • PDF
    More Data, More Relations, More Context and More Openness: A Review and Outlook for Relation Extraction
    • 3
    • PDF

    References

    SHOWING 1-8 OF 8 REFERENCES
    Distant supervision for relation extraction without labeled data
    • 1,990
    • PDF
    Structured Relation Discovery using Generative Models
    • 128
    • PDF
    Unsupervised Relation Discovery with Sense Disambiguation
    • 47
    • PDF
    Distantly supervised Web relation extraction for knowledge base population
    • 27
    • PDF
    Sentence Similarity Measures for Fine-Grained Estimation of Topical Relevance in Learner Essays
    • 17
    • PDF
    Discrete-State Variational Autoencoders for Joint Discovery and Factorization of Relations
    • 33
    • PDF
    Hierarchical Grouping to Optimize an Objective Function
    • 14,203
    • PDF
    Principal Component Analysis
    • I. T. Jolliffe
    • Computer Science
    • International Encyclopedia of Statistical Science
    • 2011
    • 6,210