Deep Recursive Neural Networks for Compositionality in Language

By Ozan Irsoy, Claire Cardie. 2014

304 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.

In Natural Language Processing

Citations in the corpus

Long Short-Term Memory-Networks for Machine Reading (2016, neutral): “4 DRNN (Irsoy and Cardie, 2014) 49.”
Representation Learning Using Multi-Task Deep Neural Networks for Semantic Classification and Information Retrieval (2015, background): “, 2014b), parse tree structure (Irsoy and Cardie, 2014), and run-time inference (Le and Mikolov, 2014).”
Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings (2016, background): “, document ranking [27], sentiment analysis [18], and question retrieval [22]).”
Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks (2015, neutral): “Fine-grained Binary RAE (Socher et al., 2013) 43.2 82.4 MV-RNN (Socher et al., 2013) 44.4 82.9 RNTN (Socher et al., 2013) 45.7 85.4 DCNN (Blunsom et al., 2014) 48.5 86.8 Paragraph-Vec (Le and Mikolov, 2014) 48.7 87.8 CNN-non-static (Kim, 2014) 48.0 87.2 CNN-multichannel (Kim, 2014) 47.4 88.1 DRNN (I”
Towards Universal Paraphrastic Sentence Embeddings (2015, methodology): “…on non-syntactic hierarchical structure (Zhao et al., 2015; Chen et al., 2015b), convolutional neural networks (Kalchbrenner et al., 2014; Kim, 2014; Hu et al., 2014; Yin & Schütze, 2015; He et al., 2015), and recu rent neural networks using long short-term memory (Tai et al., 2015; Ling et al.,…”
A Fast Unified Model for Parsing and Sentence Understanding (2016, background): “With a large but practical batch size of 512, the largest on which we tested the TreeRNN, our model is about 25 × faster than the standard CPU implementation, and about 4 × slower than the RNN baseline.”
Deep Sets (2017, background): “…deep learning (LeCun et al., 2015) has witnessed applications to other structured settings, including graphs (Bruna et al., 2013; Duvenaud et al., 2015), groups (Gens & Domingos, 2014; Christopher, 2014; Cohen & Welling, 2016), sequences and hierarchies (Irsoy & Cardie, 2014; Socher et al., 2013).”
Document Modeling with Gated Recurrent Neural Network for Sentiment Classification (2015, background): “, 2014), feature weight tuning (Li, 2014), deep recursive layer (Irsoy and Cardie, 2014), adaptive composition functions (Dong et al.”
Multimodal Convolutional Neural Networks for Matching Image and Sentence (2015, methodology): “36,41,12] and object detection [32,8]. For sentence, there is a thread of neural networks for the sentence representation, such as CNN [17,20], time-delay neural network [4], recursive neural network [15], and recurrent neural network [16,37,29,40]. The obtained sentence representation can be used f”
Text Classification Improved by Integrating Bidirectional LSTM with Two-dimensional Max Pooling (2016, background): “DRNN: Deep recursive neural networks for compositionality in language (Irsoy and Cardie, 2014).”
Discriminative Neural Sentence Modeling by Tree-Based Convolution (2015, methodology): “Irsoy and Cardie (2014) report 200 epochs for training a deep RNN, which achieves 49.8% accuracy in the 5-class sentiment classification.”
Recursive Neural Networks Can Learn Logical Semantics (2014, background): “Other strong tree-structured models have been proposed in past work (Socher et al., 2014; Irsoy and Cardie, 2014; Tai et al., 2015), but we believe that these two provide a valuable case study, and that positive results on here are likely to generalize well to stronger models.”
Cross-Modal Hierarchical Modelling for Fine-Grained Sketch Based Image Retrieval (2020, background): “While gated RvNNs [3] controlled children-to-parent information flow, Neural tree indexer (NTI) [27] used soft hierarchical structures to employ Tree-LSTMs.”