Corpus ID: 3525802

An efficient framework for learning sentence representations

@article{Logeswaran2018AnEF,
  title={An efficient framework for learning sentence representations},
  author={L. Logeswaran and H. Lee},
  journal={ArXiv},
  year={2018},
  volume={abs/1803.02893}
}
  • L. Logeswaran, H. Lee
  • Published 2018
  • Computer Science
  • ArXiv
  • In this work we propose a simple and efficient framework for learning sentence representations from unlabelled data. Drawing inspiration from the distributional hypothesis and recent work on learning sentence representations, we reformulate the problem of predicting the context in which a sentence appears as a classification problem. Given a sentence and its context, a classifier distinguishes context sentences from other contrastive sentences based on their vector representations. This allows… CONTINUE READING
    Unsupervised Learning of Sentence Representations Using Sequence Consistency
    4
    Sentence embedding with contrastive multi-views learning
    Evaluation of Sentence Representations in Polish
    2
    Probing Multilingual Sentence Representations With X-Probe
    1
    Mining Discourse Markers for Unsupervised Sentence Representation Learning
    10
    Deep Attentive Ranking Networks for Learning to Order Sentences
    1

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 49 REFERENCES
    Skip-Thought Vectors
    1460
    Learning Distributed Representations of Sentences from Unlabelled Data
    343
    Supervised Learning of Universal Sentence Representations from Natural Language Inference Data
    949
    Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks
    224
    Unsupervised Learning of Sentence Representations using Convolutional Neural Networks
    14
    Generating Sentences from a Continuous Space
    1092
    A Model of Coherence Based on Distributed Sentence Representation
    88
    Learning Generic Sentence Representations Using Convolutional Neural Networks
    70
    Discourse-Based Objectives for Fast Unsupervised Sentence Representation Learning
    51
    Distributed Representations of Sentences and Documents
    5080