Discovering Binary Codes for Documents by Learning Deep Generative Models

By Geoffrey E. Hinton, Ruslan Salakhutdinov. 2011

114 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Generative Models, Representation & Self-Supervised Learning, Signal Processing

How researchers see this paper

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

In Artificial Intelligence

1. Jianfeng Gao
2. Li Deng
3. Xiaodong He
4. Yoshua Bengio
5. Dong Yu
6. Mohit Bansal
7. Wen-tau Yih
8. Richard Socher

In Generative Models

1. Li Deng
2. Dong Yu
3. Jianfeng Gao
4. Wen-tau Yih
5. Xiaodong He
6. Jakob N. Foerster
7. Geoffry Zweig
8. Taghi M. Khoshgoftaar

In Representation & Self-Supervised Learning

1. Jianfeng Gao
2. Xiaodong He
3. Li Deng
4. Wen-tau Yih
5. Dong Yu
6. Tomas Mikolov
7. Yoav Goldberg
8. Geoffry Zweig

In Signal Processing

1. Li Deng
2. Dong Yu
3. Xiaodong He
4. Jianfeng Gao
5. Jinyu Li
6. Geoffry Zweig
7. Yoshua Bengio
8. Yifan Gong

Citations in the corpus

• Learning to Communicate with Deep Multi-Agent Reinforcement Learning (2016, methodology): “[11], and previous works on discovering binary codes for documents [12].”
• Deep Learning: Methods and Applications (2014, methodology): “1 above in this section based on the use of deep autoencoders [165, 314].”
• Modeling Interestingness with Deep Neural Networks (2014, neutral): “Hinton and Salakhutdinov (2010) propose the most original approach based on an unsupervised version of the deep neural network to discover the hierarchical semantic structure embedded in queries and documents.”
• A tutorial survey of architectures, algorithms, and applications for deep learning (2014, methodology): “Salakhutdinov and Hinton [216, 217] showed that the hidden variables in the final layer of aDBNnot only are easy to infer but also give a better representation of each document, based on the word-count features, than the widely used latent semantic analysis and the traditional TF-IDF approach for in”
• Learning Semantic Representations for the Phrase Translation Model (2013, background): “, cross entropy or mean square error [11, 12].”
• Text summarization using unsupervised deep learning (2017, background): “In information retrieval applications, it has been observed that deep generative models with only a pre-training phase are comparable with a model that has only one hidden layer (Hinton and Salakhutdinov, 2011).”
• Leveraging Deep Neural Networks and Knowledge Graphs for Entity Disambiguation (2015, unknown): “…learning of textual objects such as words, phrases, and documents with deep learning techniques (e.g., (Bengio et al., 2003; Mnih and Hin-ton, 2007; Hinton and Salakhutdinov, 2010; Col-lobert et al., 2011; Bordes et al., 2012; Huang et al., 2012; Bordes et al., 2013; Socher et al., 2013; Mikolov…”
• Linguistic Regularities in Continuous Space Word Representations (2013, background): “Also of note, the use of distributed topic representations has been studied in (Hinton and Salakhutdinov, 2006; Hinton and Salakhutdinov, 2010), and (Bordes et al.”
• Big Data: Deep Learning for financial sentiment analysis (2018, unknown): “[90, 91] propose a Deep Learning model to learn the binary codes for documents.”
• Deep learning applications and challenges in big data analytics (2015, background): “Hinton et al. [34] describe a Deep Learning generative model to learn the binary codes for documents.”
• A Latent Semantic Model with Convolutional-Pooling Structure for Information Retrieval (2014, background): “Deep architectures have been shown to be highly effective in discovering from training data the hidden structures and features at different levels of abstraction useful for a variety of tasks [32][18][20][37][7][34].”