# Cutting-off Redundant Repeating Generations for Neural Abstractive Summarization

arXiv: https://arxiv.org/abs/1701.00138 · HTML: https://mlsanity.com/paper/1701.00138/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Dec 2016.

## Built on by (most cited first, 7 of 7)

- [Conditional Generation with a Question-Answering Blueprint](https://mlsanity.com/paper/2207.00397/) (2022)
- [Rethinking Perturbations in Encoder-Decoders for Fast Training](https://mlsanity.com/paper/2104.01853/) (2021)
- [Text-Blueprint: An Interactive Platform for Plan-based Conditional Generation](https://mlsanity.com/paper/2305.00034/) (2023)
- [Taming Repetition in Dialogue Generation](https://mlsanity.com/paper/2112.08657/) (2021)
- [Towards Realistic Synthetic User-Generated Content: A Scaffolding Approach to Generating Online Discussions](https://mlsanity.com/paper/2408.08379/) (2024)
- [Unsupervised Multi-document Summarization with Holistic Inference](https://mlsanity.com/paper/2309.04087/) (2023)
- [Multi-Review Fusion-in-Context](https://mlsanity.com/paper/2403.15351/) (2024)

## Abstract (arXiv)

This paper tackles the reduction of redundant repeating generation that is often observed in RNN-based encoder-decoder models. Our basic idea is to jointly estimate the upper-bound frequency of each target vocabulary in the encoder and control the output words based on the estimation in the decoder. Our method shows significant improvement over a strong RNN-based encoder-decoder baseline and achieved its best results on an abstractive summarization benchmark.