Corpus ID: 7113872

Classify or Select: Neural Architectures for Extractive Document Summarization

@article{Nallapati2016ClassifyOS,
  title={Classify or Select: Neural Architectures for Extractive Document Summarization},
  author={Ramesh Nallapati and Bowen Zhou and M. Ma},
  journal={ArXiv},
  year={2016},
  volume={abs/1611.04244}
}
We present two novel and contrasting Recurrent Neural Network (RNN) based architectures for extractive summarization of documents. The Classifier based architecture sequentially accepts or rejects each sentence in the original document order for its membership in the summary. The Selector architecture, on the other hand, is free to pick one sentence at a time in any arbitrary order to generate the extractive summary. Our models under both architectures jointly capture the notions of salience… Expand
Hybrid MemNet for Extractive Summarization
Text Summarization using Neural Networks
Neural Extractive Summarization with Side Information
Neural Sentence Location Prediction for Summarization
Sentence Ordering and Coherence Modeling using Recurrent Neural Networks
Bottom-Up Abstractive Summarization
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 28 REFERENCES
Neural Summarization by Extracting Sentences and Words
Optimizing Sentence Modeling and Selection for Document Summarization
Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond
Enhancing Single-Document Summarization by Combining RankNet and Third-Party Sources
A Neural Attention Model for Abstractive Sentence Summarization
Document Summarization Using Conditional Random Fields
AttSum: Joint Learning of Focusing and Summarization with Neural Attention
Automatic Generation of Story Highlights
...
1
2
3
...