English

Supervised Learning of Universal Sentence Representations from Natural Language Inference Data

Computation and Language 2018-07-10 v5

Abstract

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 Natural Language Inference datasets can consistently outperform unsupervised methods like SkipThought vectors on a wide range of transfer tasks. Much like how computer vision uses ImageNet to obtain features, which can then be transferred to other tasks, our work tends to indicate the suitability of natural language inference for transfer learning to other NLP tasks. Our encoder is publicly available.

Keywords

Cite

@article{arxiv.1705.02364,
  title  = {Supervised Learning of Universal Sentence Representations from Natural Language Inference Data},
  author = {Alexis Conneau and Douwe Kiela and Holger Schwenk and Loic Barrault and Antoine Bordes},
  journal= {arXiv preprint arXiv:1705.02364},
  year   = {2018}
}

Comments

EMNLP 2017

R2 v1 2026-06-22T19:38:39.245Z