# Generating News Headlines with Recurrent Neural Networks

arXiv: https://arxiv.org/abs/1512.01712 · HTML: https://mlsanity.com/paper/1512.01712/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Dec 2015.

## Built on by (most cited first, 10 of 10)

- [Harnessing the Power of LLMs: Evaluating Human-AI Text Co-Creation through the Lens of News Headline Generation](https://mlsanity.com/paper/2310.10706/) (2023)
- [Transformer Based Implementation for Automatic Book Summarization](https://mlsanity.com/paper/2301.07057/) (2023)
- [Fact-Preserved Personalized News Headline Generation](https://mlsanity.com/paper/2501.11828/) (2025)
- [Neural Abstractive Text Summarizer for Telugu Language](https://mlsanity.com/paper/2101.07120/) (2021)
- [DeepTitle -- Leveraging BERT to generate Search Engine Optimized Headlines](https://mlsanity.com/paper/2107.10935/) (2021)
- [Text2Time: Transformer-based Article Time Period Prediction](https://mlsanity.com/paper/2304.10859/) (2023)
- [Advancements in Natural Language Processing for Automatic Text Summarization](https://mlsanity.com/paper/2502.19773/) (2025)
- [AraFinNews: Arabic Financial Summarisation with Domain-Adapted LLMs](https://mlsanity.com/paper/2511.01265/) (2025)
- [Comparision Of Adversarial And Non-Adversarial LSTM Music Generative Models](https://mlsanity.com/paper/2211.00731/) (2022)
- [Improving Sequence-to-Sequence Models for Abstractive Text Summarization Using Meta Heuristic Approaches](https://mlsanity.com/paper/2403.16247/) (2024)

## Abstract (arXiv)

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.