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.
@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}
}