Task-Oriented Learning of Word Embeddings for Semantic Relation Classification

@inproceedings{Hashimoto2015TaskOrientedLO,
  title={Task-Oriented Learning of Word Embeddings for Semantic Relation Classification},
  author={Kazuma Hashimoto and Pontus Stenetorp and Makoto Miwa and Yoshimasa Tsuruoka},
  booktitle={CoNLL},
  year={2015}
}
  • Kazuma Hashimoto, Pontus Stenetorp, +1 author Yoshimasa Tsuruoka
  • Published in CoNLL 2015
  • Computer Science
  • We present a novel learning method for word embeddings designed for relation classification. Our word embeddings are trained by predicting words between noun pairs using lexical relation-specific features on a large unlabeled corpus. This allows us to explicitly incorporate relation-specific information into the word embeddings. The learned word embeddings are then used to construct feature vectors for a relation classification model. On a well-established semantic relation classification task… CONTINUE READING
    45 Citations
    Modeling Semantic Relatedness using Global Relation Vectors
    • 2
    • Highly Influenced
    • PDF
    On the contribution of word embeddings to temporal relation classification
    • 17
    • PDF
    Unsupervised Learning of Distributional Relation Vectors
    • 18
    • Highly Influenced
    • PDF
    Feature-enriched word embeddings for named entity recognition in open-domain conversations
    • 7
    • PDF
    SeVeN: Augmenting Word Embeddings with Unsupervised Relation Vectors
    • 12
    • PDF
    Classification of Chinese Word Semantic Relations
    • 3
    • PDF
    Improved Relation Extraction with Feature-Rich Compositional Embedding Models
    • 94
    • Highly Influenced
    • PDF
    Relational Word Embeddings
    • 6
    • PDF

    References

    SHOWING 1-10 OF 38 REFERENCES
    Feature Embedding for Dependency Parsing
    • 40
    • Highly Influential
    • PDF
    Tailoring Continuous Word Representations for Dependency Parsing
    • 275
    • Highly Influential
    • PDF
    Word Representations: A Simple and General Method for Semi-Supervised Learning
    • 1,997
    • PDF
    Factor-based Compositional Embedding Models
    • 62
    • Highly Influential
    • PDF
    Semantic Compositionality through Recursive Matrix-Vector Spaces
    • 1,156
    • Highly Influential
    • PDF
    Prior Disambiguation of Word Tensors for Constructing Sentence Vectors
    • 68
    • PDF
    Simple Customization of Recursive Neural Networks for Semantic Relation Classification
    • 84
    • PDF
    Efficient Estimation of Word Representations in Vector Space
    • 16,388
    • PDF