Corpus ID: 52041633

Syntree2Vec - An algorithm to augment syntactic hierarchy into word embeddings

@article{Bhardwaj2018Syntree2VecA,
  title={Syntree2Vec - An algorithm to augment syntactic hierarchy into word embeddings},
  author={Shubham Bhardwaj},
  journal={ArXiv},
  year={2018},
  volume={abs/1808.05907}
}
  • Shubham Bhardwaj
  • Published 2018
  • Computer Science
  • ArXiv
  • Word embeddings aims to map sense of the words into a lower dimensional vector space in order to reason over them. Training embeddings on domain specific data helps express concepts more relevant to their use case but comes at a cost of accuracy when data is less. Our effort is to minimise this by infusing syntactic knowledge into the embeddings. We propose a graph based embedding algorithm inspired from node2vec. Experimental results have shown that our algorithm improves the syntactic… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Explore Further: Topics Discussed in This Paper

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 15 REFERENCES
    Dependency-Based Word Embeddings
    687
    Modeling Order in Neural Word Embeddings at Scale
    36
    Two/Too Simple Adaptations of Word2Vec for Syntax Problems
    283
    Evaluation methods for unsupervised word embeddings
    343
    SyntaxNet Models for the CoNLL 2017 Shared Task
    26
    Distributed Representations of Words and Phrases and their Compositionality
    18438
    node2vec: Scalable Feature Learning for Networks
    3166
    Evaluating Generative Models for Text Generation
    6
    Character-level Convolutional Networks for Text Classification
    2080