# Semantically Driven Sentence Fusion: Modeling and Evaluation

arXiv: https://arxiv.org/abs/2010.02592 · HTML: https://mlsanity.com/paper/2010.02592/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Oct 2020.

## Built on by (most cited first, 4 of 4)

- [EdiT5: Semi-Autoregressive Text-Editing with T5 Warm-Start](https://mlsanity.com/paper/2205.12209/) (2022)
- [Neural Pipeline for Zero-Shot Data-to-Text Generation](https://mlsanity.com/paper/2203.16279/) (2022)
- [Comparative Snippet Generation](https://mlsanity.com/paper/2206.05473/) (2022)
- [KSOD: Knowledge Supplement for LLMs On Demand](https://mlsanity.com/paper/2503.07550/) (2025)

## Abstract (arXiv)

Sentence fusion is the task of joining related sentences into coherent text. Current training and evaluation schemes for this task are based on single reference ground-truths and do not account for valid fusion variants. We show that this hinders models from robustly capturing the semantic relationship between input sentences. To alleviate this, we present an approach in which ground-truth solutions are automatically expanded into multiple references via curated equivalence classes of connective phrases. We apply this method to a large-scale dataset and use the augmented dataset for both model training and evaluation. To improve the learning of semantic representation using multiple references, we enrich the model with auxiliary discourse classification tasks under a multi-tasking framework. Our experiments highlight the improvements of our approach over state-of-the-art models.