Supervised Learning of Universal Sentence Representations from Natural Language Inference Data

@article{Conneau2017SupervisedLO,
  title={Supervised Learning of Universal Sentence Representations from Natural Language Inference Data},
  author={Alexis Conneau and Douwe Kiela and Holger Schwenk and Lo{\"i}c Barrault and Antoine Bordes},
  journal={ArXiv},
  year={2017},
  volume={abs/1705.02364}
}
  • Alexis Conneau, Douwe Kiela, +2 authors Antoine Bordes
  • Published 2017
  • Computer Science
  • ArXiv
  • Many modern NLP systems rely on word embeddings, previously trained in an unsupervised manner on large corpora, as base features. Efforts to obtain embeddings for larger chunks of text, such as sentences, have however not been so successful. Several attempts at learning unsupervised representations of sentences have not reached satisfactory enough performance to be widely adopted. In this paper, we show how universal sentence representations trained using the supervised data of the Stanford… CONTINUE READING
    1,123 Citations
    InferLite: Simple Universal Sentence Representations from Natural Language Inference Data
    • 17
    • Highly Influenced
    • PDF
    Sentence embeddings in NLI with iterative refinement encoders
    • 14
    • Highly Influenced
    • PDF
    Learning General Purpose Distributed Sentence Representations via Large Scale Multi-task Learning
    • 209
    • Highly Influenced
    • PDF
    Mining Discourse Markers for Unsupervised Sentence Representation Learning
    • 16
    • Highly Influenced
    • PDF
    Learning Better Universal Representations from Pre-trained Contextualized Language Models
    • Highly Influenced
    Learning Entailment-Based Sentence Embeddings from Natural Language Inference
    • Highly Influenced
    • PDF
    Unsupervised Learning of Sentence Representations Using Sequence Consistency
    • 6
    • Highly Influenced
    • PDF
    TRANSFER LEARNING IN NATURAL LANGUAGE PRO-
    • 3
    • Highly Influenced
    DisSent: Learning Sentence Representations from Explicit Discourse Relations
    • 25
    • Highly Influenced
    • PDF

    References

    SHOWING 1-10 OF 47 REFERENCES
    A large annotated corpus for learning natural language inference
    • 1,649
    • Highly Influential
    • PDF
    Learning Distributed Representations of Sentences from Unlabelled Data
    • 379
    • Highly Influential
    • PDF
    Natural Language Processing (Almost) from Scratch
    • 5,790
    • PDF
    Towards Universal Paraphrastic Sentence Embeddings
    • 414
    • PDF
    Skip-Thought Vectors
    • 1,606
    • Highly Influential
    • PDF
    A unified architecture for natural language processing: deep neural networks with multitask learning
    • 4,235
    • PDF
    A Simple but Tough-to-Beat Baseline for Sentence Embeddings
    • 726
    • Highly Influential
    Learning Natural Language Inference using Bidirectional LSTM model and Inner-Attention
    • 193
    • PDF
    Enriching Word Vectors with Subword Information
    • 4,332
    • PDF
    Distributed Representations of Sentences and Documents
    • 5,622
    • PDF