English

Learning Generic Sentence Representations Using Convolutional Neural Networks

Computation and Language 2017-07-28 v2 Machine Learning

Abstract

We propose a new encoder-decoder approach to learn distributed sentence representations that are applicable to multiple purposes. The model is learned by using a convolutional neural network as an encoder to map an input sentence into a continuous vector, and using a long short-term memory recurrent neural network as a decoder. Several tasks are considered, including sentence reconstruction and future sentence prediction. Further, a hierarchical encoder-decoder model is proposed to encode a sentence to predict multiple future sentences. By training our models on a large collection of novels, we obtain a highly generic convolutional sentence encoder that performs well in practice. Experimental results on several benchmark datasets, and across a broad range of applications, demonstrate the superiority of the proposed model over competing methods.

Keywords

Cite

@article{arxiv.1611.07897,
  title  = {Learning Generic Sentence Representations Using Convolutional Neural Networks},
  author = {Zhe Gan and Yunchen Pu and Ricardo Henao and Chunyuan Li and Xiaodong He and Lawrence Carin},
  journal= {arXiv preprint arXiv:1611.07897},
  year   = {2017}
}

Comments

Accepted by EMNLP 2017

R2 v1 2026-06-22T17:02:36.841Z