Global Belief Recursive Neural Networks

By Romain Paulus, Richard Socher, Christopher D. Manning. 2014

51 citations recorded by the source corpus.

How researchers see this paper

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

Citations in the corpus

Grammar Variational Autoencoder (2017, methodology): “Parse trees have been used to learn continuous representations of text in recursive neural network models (Socher et al., 2013; Irsoy & Cardie, 2014; Paulus et al., 2014).”
Neuro-Symbolic Program Synthesis (2016, methodology): “While φ ( l 1 ) and φ ( l 2 ) could be equal for leaf nodes which have the same symbol type, φ (cid:48) ( l 1 ) and φ (cid:48) ( l 2 ) will not be equal even if they have the same symbol type because they are at different positions in the tree.”
Document Modeling with Gated Recurrent Neural Network for Sentiment Classification (2015, methodology): “Recursive neural network is extended with global feedbackward (Paulus et al., 2014), feature weight tuning (Li, 2014), deep recursive layer (Irsoy and Cardie, 2014), adaptive composition functions (Dong et al., 2014), combined with Combinatory Categorial Grammar (Hermann and Blunsom, 2013), and…”
Learning Semantic Representations of Users and Products for Document Level Sentiment Classification (2015, methodology): “RNN is extended with adaptive composition functions (Dong et al., 2014), global feedbackward (Paulus et al., 2014), feature weight tuning (Li, 2014), and also used for opinion relation detection (Xu et al., 2014).”
When Are Tree Structures Necessary for Deep Learning of Representations? (2015, background): “, (Paulus et al., 2014; Irsoy and Cardie, 2014)), and applied to various NLP tasks, among them entailment (Bowman, 2013; Bowman et al.”
A review of natural language processing techniques for opinion mining systems (2017, methodology): “[134] investigated an analogous tree structured RNN for fine-grained sentiment analysis.”
Gated Neural Networks for Targeted Sentiment Analysis (2016, background): “…word representations (Socher et al. 2013; Tang et al. 2014; Vo and Zhang 2015) and deep neural network structures (Irsoy and Cardie 2013; Paulus, Socher, and Manning 2014; Kalchbrenner, Grefenstette, and Blunsom 2014; Zhou et al. 2014; Dong et al. 2014; dos Santos and Gatti 2014) have…”