# A Cascade Approach to Neural Abstractive Summarization with Content Selection and Fusion

arXiv: https://arxiv.org/abs/2010.03722 · HTML: https://mlsanity.com/paper/2010.03722/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Oct 2020.

## Built on by (most cited first, 9 of 9)

- [Smoothie: Label Free Language Model Routing](https://mlsanity.com/paper/2412.04692/) (2024)
- [Long-Span Summarization via Local Attention and Content Selection](https://mlsanity.com/paper/2105.03801/) (2021)
- [Proposition-Level Clustering for Multi-Document Summarization](https://mlsanity.com/paper/2112.08770/) (2021)
- [Controlled Text Reduction](https://mlsanity.com/paper/2210.13449/) (2022)
- [Towards Summary Candidates Fusion](https://mlsanity.com/paper/2210.08779/) (2022)
- [Decomposed Opinion Summarization with Verified Aspect-Aware Modules](https://mlsanity.com/paper/2501.17191/) (2025)
- [Implementing Deep Learning-Based Approaches for Article Summarization in Indian Languages](https://mlsanity.com/paper/2212.05702/) (2022)
- [Multi-Review Fusion-in-Context](https://mlsanity.com/paper/2403.15351/) (2024)
- [Extract-and-Abstract: Unifying Extractive and Abstractive Summarization within Single Encoder-Decoder Framework](https://mlsanity.com/paper/2409.11827/) (2024)

## Abstract (arXiv)

We present an empirical study in favor of a cascade architecture to neural text summarization. Summarization practices vary widely but few other than news summarization can provide a sufficient amount of training data enough to meet the requirement of end-to-end neural abstractive systems which perform content selection and surface realization jointly to generate abstracts. Such systems also pose a challenge to summarization evaluation, as they force content selection to be evaluated along with text generation, yet evaluation of the latter remains an unsolved problem. In this paper, we present empirical results showing that the performance of a cascaded pipeline that separately identifies important content pieces and stitches them together into a coherent text is comparable to or outranks that of end-to-end systems, whereas a pipeline architecture allows for flexible content selection. We finally discuss how we can take advantage of a cascaded pipeline in neural text summarization and shed light on important directions for future research.