Charagram: Embedding Words and Sentences via Character n-grams

@article{Wieting2016CharagramEW,
  title={Charagram: Embedding Words and Sentences via Character n-grams},
  author={J. Wieting and Mohit Bansal and Kevin Gimpel and Karen Livescu},
  journal={ArXiv},
  year={2016},
  volume={abs/1607.02789}
}
  • J. Wieting, Mohit Bansal, +1 author Karen Livescu
  • Published 2016
  • Computer Science
  • ArXiv
  • We present Charagram embeddings, a simple approach for learning character-based compositional models to embed textual sequences. A word or sentence is represented using a character n-gram count vector, followed by a single nonlinear transformation to yield a low-dimensional embedding. We use three tasks for evaluation: word similarity, sentence similarity, and part-of-speech tagging. We demonstrate that Charagram embeddings outperform more complex architectures based on character-level… CONTINUE READING
    152 Citations
    VCWE: Visual Character-Enhanced Word Embeddings
    • 5
    • PDF
    Generalizing Word Embeddings using Bag of Subwords
    • 24
    • PDF
    Mimicking Word Embeddings using Subword RNNs
    • 96
    • PDF
    Character and Subword-Based Word Representation for Neural Language Modeling Prediction
    • 11
    • PDF
    cw2vec: Learning Chinese Word Embeddings with Stroke n-gram Information
    • 47
    • PDF
    Segmentation-free compositional n-gram embedding
    • 4
    • PDF
    Unsupervised Learning of Sentence Embeddings using Compositional n-Gram Features
    • 344
    • PDF
    Deep contextualized word representations
    • 5,199
    • PDF

    References

    SHOWING 1-10 OF 70 REFERENCES
    Text segmentation with character-level text embeddings
    • 27
    • PDF
    Finding Function in Form: Compositional Character Models for Open Vocabulary Word Representation
    • 520
    • Highly Influential
    • PDF
    Joint Learning of Character and Word Embeddings
    • 202
    • PDF
    Multi-Perspective Sentence Similarity Modeling with Convolutional Neural Networks
    • 288
    • PDF
    Jointly optimizing word representations for lexical and sentential tasks with the C-PHRASE model
    • 46
    • Highly Influential
    • PDF
    Co-learning of Word Representations and Morpheme Representations
    • 88
    • PDF
    Deep Unordered Composition Rivals Syntactic Methods for Text Classification
    • 542
    • PDF
    Character-Aware Neural Language Models
    • 1,263
    • Highly Influential
    • PDF