Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks

Keywords

Computer science, Treebank, Artificial intelligence, Natural language processing, Recurrent neural network

References

• Compositional Matrix-Space Models for Sentiment AnalysisAinur Yessenalina, Claire Cardie — 2011
• Parsing Natural Scenes and Natural Language with Recursive Neural NetworksRichard Socher, Cliff Chiung-Yu Lin, Christopher D. Manning — 2011
• Learning representations by back-propagating errorsDavid E. Rumelhart, Geoffrey E. Hinton, Ronald J. Williams — 1986
• Learning to ExecuteWojciech Zaremba, Ilya Sutskever — 2014
• Convolutional Neural Networks for Sentence ClassificationYoon Kim — 2014
• Modeling Documents with Deep Boltzmann MachinesNitish Srivastava, Ruslan Salakhutdinov, Geoffrey E. Hinton — 2013
• Semantic Compositionality through Recursive Matrix-Vector SpacesRichard Socher, Brody Huval, Christopher D. Manning — 2012
• Show and tell: A neural image caption generatorOriol Vinyals, Alexander Toshev, Samy Bengio — 2014
• Improving neural networks by preventing co-adaptation of feature detectorsGeoffrey E. Hinton, Nitish Srivastava, Alex Krizhevsky — 2012
• A Solution to Plato's Problem: The Latent Semantic Analysis Theory of Acquisition, Induction, and Representation of Knowledge.Thomas K. Landauer, Susan Dumais — 1997
• Composition in Distributional Models of SemanticsJeff Mitchell, Mirella Lapata — 2010
• Hybrid speech recognition with Deep Bidirectional LSTMAlex Graves, Navdeep Jaitly, Abdelrahman Mohamed — 2013
• Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber — 1997
• The Vanishing Gradient Problem During Learning Recurrent Neural Nets and Problem SolutionsSepp Hochreiter — 1998
• The Measurement of Textual Coherence with Latent Semantic Analysis.Peter W. Foltz, Walter Kintsch, Thomas K. Landauer — 1998
• Dropout: a simple way to prevent neural networks from overfittingNitish Srivastava, Geoffrey E. Hinton, Alex Krizhevsky — 2014
• Accurate Unlexicalized ParsingDan Klein, Christopher D. Manning — 2003
• ECNU: One Stone Two Birds: Ensemble of Heterogenous Measures for Semantic Relatedness and Textual EntailmentJiang Zhao, Tiantian Zhu, Man Lan — 2014
• Learning long-term dependencies with gradient descent is difficultYoshua Bengio, P. Simard, Paolo Frasconi — 1994
• Finding Structure in TimeJeffrey L. Elman — 1990

Cited by

• Dependency-based Siamese long short-term memory network for learning sentence representationsTerri Goldstein — 2018
• Chemical–gene relation extraction using recursive neural networkSabrina Gentlewarrior — 2018
• Distilling Word Embeddings: An Encoding ApproachLili Mou, Ran Jia, Yan Xu — 2015
• Do Multi-Sense Embeddings Improve Natural Language Understanding?Jiwei Li, Dan Jurafsky — 2015
• Tree-based Convolution: A New Neural Architecture for Sentence ModelingLili Mou, Hao Peng, Ge Li — 2015
• Learning multi-faceted representations of individuals from heterogeneous evidence using neural networksJiwei Li, Alan Ritter, Dan Jurafsky — 2015
• Recursive Neural Networks Can Learn Logical SemanticsSamuel R. Bowman, Christopher Potts, Christopher D. Manning — 2014
• When Are Tree Structures Necessary for Deep Learning of Representations?Jiwei Li, Thang Luong, Dan Jurafsky — 2015
• Molding CNNs for text: non-linear, non-consecutive convolutionsTao Leí, Regina Barzilay, Tommi Jaakkola — 2015
• Long Short-Term Memory Over Recursive StructuresXiaodan Zhu, Parinaz Sobihani, Hongyu Guo — 2015
• A Primer on Neural Network Models for Natural Language ProcessingYoav Goldberg — 2015
• Language Understanding for Text-based Games using Deep Reinforcement LearningKarthik Narasimhan, Tejas Kulkarni, Regina Barzilay — 2015
• Enhanced Word Embeddings from a Hierarchical Neural Language ModelXun Wang, Katsuhoto Sudoh, Masaaki Nagata — 2015
• Dependency Recurrent Neural Language Models for Sentence CompletionPiotr Mirowski, Andreas Vlachos — 2015
• Tree-Structured Composition in Neural Networks without Tree-Structured ArchitecturesSamuel R. Bowman, Christopher D. Manning, Christopher Potts — 2015
• Deep learning for sentiment analysis: successful approaches and future challengesDuyu Tang, Bing Qin, Ting Liu — 2015
• Towards Universal Paraphrastic Sentence EmbeddingsJohn Wieting, Mohit Bansal, Kevin Gimpel — 2015
• A Generative Model of Words and Relationships from Multiple SourcesStephanie L. Hyland, Theofanis Karaletsos, Gunnar Rätsch — 2015
• Dense Recurrent Neural Networks for Scene LabelingBing Shuai, Zhen Zuo, Bing Wang — 2018
• Multi-Source Neural TranslationBarret Zoph, Kevin Knight — 2016

Related papers

• Efficient Estimation of Word Representations in Vector SpaceTomáš Mikolov, Kai Chen, Greg S. Corrado — 2013
• Attention is All you NeedAshish Vaswani, Noam Shazeer, Niki Parmar — 2017
• Recursive Deep Models for Semantic Compositionality Over a Sentiment TreebankRichard Socher, Alex Perelygin, Jean Y. Wu — 2013
• GloVe: Global Vectors for Word RepresentationJeffrey Pennington, Richard Socher, Christopher D. Manning — 2014
• Dropout: a simple way to prevent neural networks from overfittingNitish Srivastava, Geoffrey E. Hinton, Alex Krizhevsky — 2014