Unsupervised Learning of Sentence Representations using Convolutional Neural Networks

By Zhe Gan, Yunchen Pu, Ricardo Henao, Chunyuan Li, Xiaodong He, Lawrence Carin. 2016

20 citations recorded by the source corpus.

Subfields: Natural Language Processing, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

1. Lawrence Carin
2. Zhe Gan
3. Samuel R. Bowman
4. Jianfeng Gao
5. Yonatan Belinkov
6. C. Pal
7. Yizhe Zhang
8. Dinghan Shen

In Representation & Self-Supervised Learning

1. Honglak Lee
2. Yoshua Bengio
3. Lawrence Carin
4. Samuel R. Bowman
5. C. Pal
6. Lajanugen Logeswaran
7. Zhe Gan
8. Dinghan Shen

Citations in the corpus

• An efficient framework for learning sentence representations (2018, methodology): “Drawing inspiration from this model, Gan et al. (2016) explore the use of convolutional neural network (CNN) encoders.”
• Discourse-Based Objectives for Fast Unsupervised Sentence Representation Learning (2017, methodology): “Since that work, three other papers have presented improvements to this method (the SDAE of Hill et al. 2016, also Gan et al. 2016; Ramachandran et al. 2016).”
• Learning General Purpose Distributed Sentence Representations via Large Scale Multi-task Learning (2018, methodology): “Hill et al. (2016) address this by considering faster alternatives such as sequential denoising autoencoders and shallow log-linear models.”
• Adversarial Feature Matching for Text Generation (2017, methodology): “Toward this end, we initialize the LSTM parameters of the generator by pre-training a standard CNN-LSTM autoencoder (Gan et al., 2016).”