Distant Supervision for Relation Extraction via Piecewise Convolutional Neural Networks

@inproceedings{Zeng2015DistantSF,
  title={Distant Supervision for Relation Extraction via Piecewise Convolutional Neural Networks},
  author={Daojian Zeng and Kang Liu and Yubo Chen and Jun Zhao},
  booktitle={EMNLP},
  year={2015}
}
  • Daojian Zeng, Kang Liu, +1 author Jun Zhao
  • Published in EMNLP 2015
  • Computer Science
  • Two problems arise when using distant supervision for relation extraction. [...] Key Method To solve the first problem, distant supervised relation extraction is treated as a multi-instance problem in which the uncertainty of instance labels is taken into account. To address the latter problem, we avoid feature engineering and instead adopt convolutional architecture with piecewise max pooling to automatically learn relevant features. Experiments show that our method is effective and outperforms several…Expand Abstract
    577 Citations
    Self-Attention Enhanced CNNs and Collaborative Curriculum Learning for Distantly Supervised Relation Extraction
    • 9
    • Highly Influenced
    • PDF
    Relation Extraction with Multi-instance Multi-label Convolutional Neural Networks
    • 63
    • Highly Influenced
    • PDF
    Neural Relation Extraction with Selective Attention over Instances
    • 559
    • Highly Influenced
    • PDF
    Multi-Path Convolutional Neural Network for Distant Supervised Relation Extraction
    • 1
    • Highly Influenced
    Robust Distant Supervision Relation Extraction via Deep Reinforcement Learning
    • 103
    • Highly Influenced
    • PDF
    Distant Supervision for Relation Extraction with Neural Instance Selector
    • Highly Influenced
    • PDF
    Relation Extraction via Position-Enhanced Convolutional Neural Network
    • Weiwei Shi, Sheng Gao
    • Computer Science
    • 2017 International Conference on Intelligent Environments (IE)
    • 2017
    • 4
    • Highly Influenced
    Distant Supervision for Relation Extraction via Piecewise Attention and Bag-Level Contextual Inference
    • 3
    • Highly Influenced

    References

    SHOWING 1-10 OF 29 REFERENCES
    Modeling Relations and Their Mentions without Labeled Text
    • 816
    • Highly Influential
    • PDF
    Multi-instance Multi-label Learning for Relation Extraction
    • 590
    • Highly Influential
    • PDF
    Relation Classification via Convolutional Deep Neural Network
    • 1,038
    • PDF
    Knowledge-Based Weak Supervision for Information Extraction of Overlapping Relations
    • 738
    • Highly Influential
    • PDF
    Distant supervision for relation extraction without labeled data
    • 2,061
    • Highly Influential
    • PDF
    Adapting RBF Neural Networks to Multi-Instance Learning
    • M. Zhang, Z. Zhou
    • Mathematics, Computer Science
    • Neural Processing Letters
    • 2005
    • 62
    • PDF
    Natural Language Processing (Almost) from Scratch
    • 5,843
    • Highly Influential
    • PDF
    Exploring Various Knowledge in Relation Extraction
    • 630
    • PDF
    Why Does Unsupervised Pre-training Help Deep Learning?
    • 1,293
    • PDF
    Learning Representations for Weakly Supervised Natural Language Processing Tasks
    • 55
    • PDF