Generating News Headlines with Recurrent Neural Networks
arXiv:1512.01712
Abstract
We describe an application of an encoder-decoder recurrent neural network with LSTM units and attention to generating headlines from the text of news articles. We find that the model is quite effective at concisely paraphrasing news articles. Furthermore, we study how the neural network decides which input words to pay attention to, and specifically we identify the function of the different neurons in a simplified attention mechanism. Interestingly, our simplified attention mechanism performs better that the more complex attention mechanism on a held out set of articles.
References in corpus (7)
- Sequence to Sequence Learning with Neural Networks
- Teaching Machines to Read and Comprehend
- Recurrent Neural Network Regularization
- Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
- Effective Approaches to Attention-based Neural Machine Translation
- Listen, Attend and Spell
- Joint Training of Deep Boltzmann Machines
Cited by in corpus (16)
- Neural Abstractive Text Summarization with Sequence-to-Sequence Models
- Distraction-Based Neural Networks for Document Summarization
- Controlling Output Length in Neural Encoder-Decoders
- Abstractive and Extractive Text Summarization using Document Context Vector and Recurrent Neural Networks
- Deep Recurrent Generative Decoder for Abstractive Text Summarization
- A Semantic Relevance Based Neural Network for Text Summarization and Text Simplification
- Bengali Abstractive News Summarization(BANS): A Neural Attention Approach
- Outline Generation: Understanding the Inherent Content Structure of Documents
- Improving Semantic Relevance for Sequence-to-Sequence Learning of Chinese Social Media Text Summarization
- This Email Could Save Your Life: Introducing the Task of Email Subject Line Generation
- Fact-Preserved Personalized News Headline Generation
- DeepTitle -- Leveraging BERT to generate Search Engine Optimized Headlines
- Improving Abstractive Text Summarization with History Aggregation
- Abstractive Headline Generation for Spoken Content by Attentive Recurrent Neural Networks with ASR Error Modeling
- Abstractive Summarization Improved by WordNet-based Extractive Sentences
- Order-Preserving Abstractive Summarization for Spoken Content Based on Connectionist Temporal Classification