Learning generic sentence representations using convolutional neural networks

Published

Conference Paper

© 2017 Association for Computational Linguistics. 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.

Duke Authors

Cited Authors

  • Gan, Z; Pu, Y; Henao, R; Li, C; He, X; Carin, L

Published Date

  • January 1, 2017

Published In

  • Emnlp 2017 Conference on Empirical Methods in Natural Language Processing, Proceedings

Start / End Page

  • 2390 - 2400

International Standard Book Number 13 (ISBN-13)

  • 9781945626838

Citation Source

  • Scopus