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}
}
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

Citations

Publications citing this paper.
SHOWING 1-10 OF 31 CITATIONS

Unsupervised Learning of Distributional Relation Vectors

VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Modeling Semantic Relatedness using Global Relation Vectors

VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

DRAFT On Machine Perception of Sound Ph

VIEW 3 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Boosting Causal Embeddings via Potential Verb-Mediated Causal Patterns

VIEW 2 EXCERPTS
CITES METHODS & BACKGROUND

Classifying medical relations in clinical text via convolutional neural networks

VIEW 1 EXCERPT

Overview of Knowledge Mapping Construction Technology

  • Tongliang Lu, Xichun Hu
  • Computer Science
  • 2019 IEEE 8th Joint International Information Technology and Artificial Intelligence Conference (ITAIC)
  • 2019
VIEW 1 EXCERPT
CITES METHODS

Relational Word Embeddings

VIEW 2 EXCERPTS
CITES BACKGROUND

Sentiment-Aware Short Text Classification Based on Convolutional Neural Network and Attention

VIEW 1 EXCERPT
CITES BACKGROUND

References

Publications referenced by this paper.
SHOWING 1-10 OF 27 REFERENCES

Factor-based Compositional Embedding Models

  • Mo Yu
  • Computer Science
  • 2014
VIEW 12 EXCERPTS
HIGHLY INFLUENTIAL

Relation Classification via Convolutional Deep Neural Network

VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

Feature Embedding for Dependency Parsing

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Adaptive Subgradient Methods for Online Learning and Stochastic Optimization

VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL