· 2013
Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank
- 6,800citations
- 2013year
Short summary
A novel recursive deep learning model achieves state-of-the-art accuracy (85%) in predicting sentiment from sentences by learning compositional meaning.
AI-generated from the title and abstract; the full text is not read.
Key points
- Introduced a recursive deep learning model for sentiment analysis.
- Achieved 85% accuracy on the Stanford Sentiment Treebank, a new state-of-the-art at the time.
- Model learns compositional sentiment by recursively applying neural networks to parse trees.
- Effectively captures how individual word sentiments combine to form sentence sentiment.
AI-generated from the title and abstract; the full text is not read.
Abstract
Richard Socher, Alex Perelygin, Jean Wu, Jason Chuang, Christopher D. Manning, Andrew Ng, Christopher Potts. Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing. 2013.
The authors' abstract, as published at the source., 2013 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Artificial Intelligence
Artificial IntelligenceComputer Science