Corpus ID: 629094

Word Representations: A Simple and General Method for Semi-Supervised Learning

@inproceedings{Turian2010WordRA,
  title={Word Representations: A Simple and General Method for Semi-Supervised Learning},
  author={Joseph P. Turian and Lev-Arie Ratinov and Yoshua Bengio},
  booktitle={ACL},
  year={2010}
}
  • Joseph P. Turian, Lev-Arie Ratinov, Yoshua Bengio
  • Published in ACL 2010
  • Computer Science
  • If we take an existing supervised NLP system, a simple and general way to improve accuracy is to use unsupervised word representations as extra word features. We evaluate Brown clusters, Collobert and Weston (2008) embeddings, and HLBL (Mnih & Hinton, 2009) embeddings of words on both NER and chunking. We use near state-of-the-art supervised baselines, and find that each of the three word representations improves the accuracy of these baselines. We find further improvements by combining… CONTINUE READING
    1,964 Citations

    Figures, Tables, and Topics from this paper.

    Multi-View Learning of Word Embeddings via CCA
    • 237
    • Highly Influenced
    • PDF
    Improving Word Representations via Global Context and Multiple Word Prototypes
    • 1,065
    • PDF
    Word Embeddings vs Word Types for Sequence Labeling: the Curious Case of CV Parsing
    • 8
    • PDF
    Substitute Based SCODE Word Embeddings in Supervised NLP Tasks
    • 2
    • Highly Influenced
    • PDF
    Tailoring Continuous Word Representations for Dependency Parsing
    • 272
    • Highly Influenced
    • PDF
    Re-embedding words
    • 90
    • Highly Influenced
    • PDF
    Delta-training: Simple Semi-Supervised Text Classification using Pretrained Word Embeddings
    • 2
    • PDF
    VecShare: A Framework for Sharing Word Representation Vectors
    • 2
    • PDF
    Deep contextualized word representations
    • 4,595
    • PDF

    References

    SHOWING 1-10 OF 63 REFERENCES
    A Preliminary Evaluation of Word Representations for Named-Entity Recognition
    • 28
    • PDF
    Semi-Supervised Sequential Labeling and Segmentation Using Giga-Word Scale Unlabeled Data
    • 151
    • Highly Influential
    • PDF
    Distributional Representations for Handling Sparsity in Supervised Sequence-Labeling
    • 95
    • PDF
    Simple Semi-supervised Dependency Parsing
    • 489
    • Highly Influential
    • PDF
    A High-Performance Semi-Supervised Learning Method for Text Chunking
    • 224
    • Highly Influential
    • PDF
    A unified architecture for natural language processing: deep neural networks with multitask learning
    • 4,112
    • Highly Influential
    • PDF
    Semi-Supervised Sequence Modeling with Syntactic Topic Models
    • 66
    • PDF
    Semi-Supervised Learning for Natural Language
    • 340
    • Highly Influential
    • PDF
    Improving generative statistical parsing with semi-supervised word clustering
    • 89
    • PDF