Corpus ID: 990233

Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank

@inproceedings{Socher2013RecursiveDM,
  title={Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank},
  author={R. Socher and Alex Perelygin and J. Wu and Jason Chuang and Christopher D. Manning and A. Ng and Christopher Potts},
  booktitle={EMNLP},
  year={2013}
}
  • R. Socher, Alex Perelygin, +4 authors Christopher Potts
  • Published in EMNLP 2013
  • Computer Science
  • Semantic word spaces have been very useful but cannot express the meaning of longer phrases in a principled way. [...] Key Method To address them, we introduce the Recursive Neural Tensor Network. When trained on the new treebank, this model outperforms all previous methods on several metrics. It pushes the state of the art in single sentence positive/negative classification from 80% up to 85.4%. The accuracy of predicting fine-grained sentiment labels for all phrases reaches 80.7%, an improvement of 9.7% over…Expand Abstract
    4,101 Citations

    Figures, Tables, and Topics from this paper

    Explore Further: Topics Discussed in This Paper

    Recurrent versus Recursive Approaches Towards Compositionality in Semantic Vector
    • Highly Influenced
    • PDF
    Learning vector representations for sentences: The recursive deep learning approach
    • PDF
    A Sentiment Treebank and Morphologically Enriched Recursive Deep Models for Effective Sentiment Analysis in Arabic
    • 35
    • Highly Influenced
    • PDF
    Adaptive Multi-Compositionality for Recursive Neural Models with Applications to Sentiment Analysis
    • 63
    • Highly Influenced
    • PDF
    Leveraging Multi-grained Sentiment Lexicon Information for Neural Sequence Models
    • 2
    • Highly Influenced
    • PDF
    Deep Convolutional Neural Networks for Sentiment Analysis of Short Texts
    • 934
    • Highly Influenced
    • PDF
    Encoding Syntactic Knowledge in Neural Networks for Sentiment Classification
    • 56
    • Highly Influenced
    • PDF

    References

    SHOWING 1-10 OF 55 REFERENCES
    Semantic Compositionality through Recursive Matrix-Vector Spaces
    • 1,156
    • PDF
    Semi-Supervised Recursive Autoencoders for Predicting Sentiment Distributions
    • 1,146
    • PDF
    Compositional Matrix-Space Models for Sentiment Analysis
    • 154
    • PDF
    Distributional Memory: A General Framework for Corpus-Based Semantics
    • 578
    • PDF
    Multi-entity Sentiment Scoring
    • 40
    • PDF
    Dependency Tree-based Sentiment Classification using CRFs with Hidden Variables
    • 341
    • PDF
    Sentiment Composition
    • 184
    • PDF
    A unified architecture for natural language processing: deep neural networks with multitask learning
    • 4,221
    • PDF
    Improving Word Representations via Global Context and Multiple Word Prototypes
    • 1,082
    • PDF