Long Short-Term Memory Over Recursive Structures

By Xiao-Dan Zhu, Parinaz Sobhani, Hongyu Guo. 2015

347 citations recorded by the source corpus.

Subfields: Natural Language Processing, Model Architectures

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

In Model Architectures

Citations in the corpus

Enhanced LSTM for Natural Language Inference (2016, methodology): “s continues and results in a full binary tree, where padding words are inserted to the nodes when there are no enough leaves to form a full tree. Each tree node is implemented with a tree-LSTM block [Zhu et al., 2015]. Table 2 depicts that with this replacement, the performance drops to 88.1%, showi”
Understanding Neural Networks through Representation Erasure (2016, methodology): “It is worth noting that the BiLSTM model achieves state-of-the-art performance in sentence-level fine-grained classification on this benchmark, significantly outperforming tree-based models, namely 50.1 reported in Zhu et al. (2015) and 51.0 in Tai et al. (2015).”
Junction Tree Variational Autoencoder for Molecular Graph Generation (2018, methodology): “Tree-structured Models Our tree encoder is related to recursive neural networks and tree-LSTM (Socher et al., 2013; Tai et al., 2015; Zhu et al., 2015).”
Neural Tree Indexers for Text Understanding (2016, methodology): “For non-leaf node, we adopt S-LSTM Zhu et al. (2015), an extension of LSTM to tree structures, to learn a node representation by its children nodes.”
Text Classification Improved by Integrating Bidirectional LSTM with Two-dimensional Max Pooling (2016, background): “S-LSTM: Long short-term memory over recursive structures (Zhu et al., 2015).”
Exploring Question Understanding and Adaptation in Neural-Network-Based Question Answering (2017, methodology): “More speciﬁcally, we explore a tree-structured LSTM [Zhu et al., 2015, Tai et al., 2015] which extends the linear-chain long short-term memory (LSTM) [Hochreiter and Schmidhuber, 1997] to a recursive structure, which has the potential to capture long-distance interactions over the structures.”
Multi-Perspective Sentence Similarity Modeling with Convolutional Neural Networks (2015, background): “Most recently, Tai et al. (2015) and Zhu et al. (2015) concurrently proposed a tree-based LSTM neural network architecture for sentence modeling.”
Pre-trained models for natural language processing: A survey (2020, methodology): “Some popular non-sequence models include Recursive NN [159], TreeLSTM [174, 222], and GCN [88].”
A Primer on Neural Network Models for Natural Language Processing (2015, methodology): “Works using the reranking approach include (Socher et al., 2013; Auli et al., 2013; Le & Zuidema, 2014; Zhu et al., 2015a) MEMM and hybrid approaches Other formulations are, of course, also possible.”
Tree-to-tree Neural Networks for Program Translation (2018, methodology): “Recently, various neural networks with tree structures have been proposed to employ the structural information of the data [11, 26, 25, 32, 3, 29, 34, 27, 13, 33, 28, 18, 6].”
Supervised and Semi-Supervised Text Categorization using LSTM for Region Embeddings (2016, methodology): “It has been also used for representing short sentences mostly for sentiment analysis, and some of them rely on syntactic parse trees; see e.g., (Zhu et al., 2015; Tang et al., 2015; Tai et al., 2015; Le & Zuidema, 2015).”
Pairwise Word Interaction Modeling with Deep Neural Networks for Semantic Similarity Measurement (2016, background): “Tai et al. (2015) and Zhu et al. (2015) concurrently proposed tree-structured long short-term memory networks, which recursively construct sentence representations following their syntactic trees.”
A Survey on Text Classification: From Shallow to Deep Learning (2020, background): “…classification – the procedure of designating pre-defined labels for text – is an essential and significant task in many Natural Language Processing (NLP) applications, such as sentiment analysis [1][2] [3], topic labeling [4] [5] [6], question answering [7] [8] and dialog act classification [9].”
Aspect Level Sentiment Classification with Attention-over-Attention Neural Networks (2018, methodology): “Classical methods include Convolutional Neural Networks [7], Recurrent Neural Networks [9,24], Recursive Neural Networks [19,29].”
Substructure Substitution: Structured Data Augmentation for NLP (2021, background): “Shi et al. (2018b) argue that binary balanced trees are better backbones for recursive neural networks (Zhu et al., 2015; Tai et al., 2015) on text classiﬁcation.”
Sentiment Analysis: Detecting Valence, Emotions, and Other Affectual States from Text (2016, background): “Work by Kalchbrenner, Grefenstette, and Blunsom (2014), Zhu, Sobhani, and Guo (2015), Wang, Yu, Lai, and Zhang (2016), and others further explored the use recursive neural networks and word embeddings in sentiment analysis.”
Measuring the Information Content of Financial News (2016, methodology): “A syntactic approach for modeling a sentence s is to use a tree-structured LSTM (Tree-LSTM), embedding the parse tree of a sentence (Le and Zuidema, 2015; Tai et al., 2015; Zhu et al., 2015; Miwa and Bansal, 2016).”