# Learning to Fuse Sentences with Transformers for Summarization

arXiv: https://arxiv.org/abs/2010.03726 · HTML: https://mlsanity.com/paper/2010.03726/

## Key facts

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

## Built on by (most cited first, 14 of 14)

- [Attribute First, then Generate: Locally-attributable Grounded Text Generation](https://mlsanity.com/paper/2403.17104/) (2024)
- [Smoothie: Label Free Language Model Routing](https://mlsanity.com/paper/2412.04692/) (2024)
- [QA-Align: Representing Cross-Text Content Overlap by Aligning Question-Answer Propositions](https://mlsanity.com/paper/2109.12655/) (2021)
- [DecipherPref: Analyzing Influential Factors in Human Preference Judgments via GPT-4](https://mlsanity.com/paper/2305.14702/) (2023)
- [Summarization Programs: Interpretable Abstractive Summarization with Neural Modular Trees](https://mlsanity.com/paper/2209.10492/) (2022)
- [Dissecting Generation Modes for Abstractive Summarization Models via Ablation and Attribution](https://mlsanity.com/paper/2106.01518/) (2021)
- [TLDR9+: A Large Scale Resource for Extreme Summarization of Social Media Posts](https://mlsanity.com/paper/2110.01159/) (2021)
- [Controlled Text Reduction](https://mlsanity.com/paper/2210.13449/) (2022)
- [Generating EDU Extracts for Plan-Guided Summary Re-Ranking](https://mlsanity.com/paper/2305.17779/) (2023)
- [Towards Summary Candidates Fusion](https://mlsanity.com/paper/2210.08779/) (2022)
- [Non-autoregressive Text Editing with Copy-aware Latent Alignments](https://mlsanity.com/paper/2310.07821/) (2023)
- [The Power of Summary-Source Alignments](https://mlsanity.com/paper/2406.00842/) (2024)
- [Source Identification in Abstractive Summarization](https://mlsanity.com/paper/2402.04677/) (2024)
- [Multi-Review Fusion-in-Context](https://mlsanity.com/paper/2403.15351/) (2024)

## Abstract (arXiv)

The ability to fuse sentences is highly attractive for summarization systems because it is an essential step to produce succinct abstracts. However, to date, summarizers can fail on fusing sentences. They tend to produce few summary sentences by fusion or generate incorrect fusions that lead the summary to fail to retain the original meaning. In this paper, we explore the ability of Transformers to fuse sentences and propose novel algorithms to enhance their ability to perform sentence fusion by leveraging the knowledge of points of correspondence between sentences. Through extensive experiments, we investigate the effects of different design choices on Transformer's performance. Our findings highlight the importance of modeling points of correspondence between sentences for effective sentence fusion.