Learning Continuous Phrase Representations and Syntactic Parsing with Recursive Neural Networks

By Richard Socher, Christopher D. Manning, Andrew Y. Ng. 2010

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

Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank (2013, methodology): “Hence, δ p 2 ,com = δ p 2 ,s which we can use to obtain the standard backprop derivative for W (Goller and K¨uchler, 1996; Socher et al., 2010).”
Learning Dense Representations of Phrases at Scale (2020, background): “, 2014) or syntactic parsing (Socher et al., 2010), our work focuses on learning dense phrase representations for QA and any other knowledge-intensive tasks where phrases can be easily retrieved by performing MIPS.”
Grounded Compositional Semantics for Finding and Describing Images with Sentences (2014, background): “Since words rarely appear in isolation, the task of learning compositional meaning representations for longer phrases has recently received a lot of attention (Mitchell and Lapata, 2010; Socher et al., 2010; Socher et al., 2012; Grefenstette et al., 2013).”
Order Matters: Sequence to sequence for sets (2015, neutral): “Similarly, we do not want to assume a known structured input, as is done for instance with recursive neural networks (Socher et al., 2010) which encode sentences recursively as (given) trees.”
Self-Adaptive Hierarchical Sentence Model (2015, background): “There has been a surge of sentence models with the order of words incorporated, mostly based on neural networks of various forms, including recursive neural networks [Socher et al., 2010; 2012; 2013], recurrent neural network [Irsoy and Cardie, 2014; Lai et al.”
Distilling Task-Specific Knowledge from BERT into Simple Neural Networks (2019, background): “In the past, researchers have developed and applied various neural architectures for NLP, including convolutional neural networks (Kalchbrenner et al., 2014; Kim, 2014), recurrent neural networks (Mikolov et al., 2010, 2011; Graves, 2013), and recursive neural networks (Socher et al., 2010, 2011).”
Towards Open Set Deep Networks (2015, methodology): “Altough a range of algorithms has been developed to address this issue [4, 20, 21, 25, 2], performing open set recognition with deep networks has remained an unsolved problem.”
Deep Learning: Methods and Applications (2014, background): “In the earlier work by the same research group (Socher et al., 2011), a recursive neural network with local context was developed to build a deep architecture.”
Practical Recommendations for Gradient-Based Training of Deep Architectures (2012, methodology): “This idea has been generalized from sequences and 2-D images to arbitrary graphs with recursive neural networks or recursive graphical models (Pollack, 1990; Frasconi et al., 1998; Bottou, 2011; Socher et al., 2011), Markov Logic Networks (Richardson and Domingos, 2006) and relational learning (Geto”
From machine learning to machine reasoning (2011, methodology): “Socher et al. (2010) independently trained a similar system in a supervised manner using the WSJ section of the annotated Penn TreeBank corpus.”
From Paraphrase Database to Compositional Paraphrase Model and Back (2015, background): “We find improved performance by training a recursive neural network (RNN; Socher et al., 2010) directly on phrase pairs from PPDB.”
Easy-First Dependency Parsing with Hierarchical Tree LSTMs (2016, methodology): “, 2015; Watanabe and Sumita, 2015); bottom up parsers that rely solely on recursively combined vector encodings of subtrees (Socher et al., 2010; Stenetorp, 2013; Socher et al., 2013a); and parse-reranking approaches that first produce a k-best list of parses using a traditional parsing technique, a”
Template-Based Math Word Problem Solvers with Recursive Neural Networks (2019, background): “(Socher, Manning, and Ng 2010) introduced a context-aware Recursive NN to learn vector space representations for variable-sized inputs and predict the phrase structure.”
A tutorial survey of architectures, algorithms, and applications for deep learning (2014, background): “Specifically, as reported in [86], the recursive structure commonly found in natural scene images and in natural language sentences can be discovered using a max-margin structure prediction architecture.”