• Publications
  • Influence
Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank
TLDR
We introduce the Stanford Sentiment Treebank and a powerful Recursive Neural Tensor Network that can accurately predict the compositional semantic effects present in this new corpus. Expand
  • 4,101
  • 645
  • PDF
Semantic Compositionality and Deep Learning for Sentiment Analysis
TLDR
We introduce a new dataset that includes detailed sentiment information at all nodes in parse trees describing movie review sentences, which improves all classification models, including baselines. Expand
  • 1
  • PDF
Detecting Audio / Video Asynchrony
Asynchrony between the audio and video track in streaming video can cause user frustration with the service but often goes unreported. Providers of on-demand internet streaming media such as NetflixExpand
  • 1
  • PDF
Optimal Feature Extraction based Machine Learning Approach for Sarcasm Type Detection in News Headlines
TLDR
Sarcasm detection is one of the most difficult tasks in natural language processing. Expand