# Data-to-Text Generation with Iterative Text Editing

arXiv: https://arxiv.org/abs/2011.01694 · HTML: https://mlsanity.com/paper/2011.01694/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Nov 2020.

## Built on by (most cited first, 11 of 11)

- [Controlling Hallucinations at Word Level in Data-to-Text Generation](https://mlsanity.com/paper/2102.02810/) (2021)
- [Text Generation with Text-Editing Models](https://mlsanity.com/paper/2206.07043/) (2022)
- [Neural Pipeline for Zero-Shot Data-to-Text Generation](https://mlsanity.com/paper/2203.16279/) (2022)
- [Answering Ambiguous Questions via Iterative Prompting](https://mlsanity.com/paper/2307.03897/) (2023)
- [Innovations in Neural Data-to-text Generation: A Survey](https://mlsanity.com/paper/2207.12571/) (2022)
- [Converge to the Truth: Factual Error Correction via Iterative Constrained Editing](https://mlsanity.com/paper/2211.12130/) (2022)
- [Mind the Labels: Describing Relations in Knowledge Graphs With Pretrained Models](https://mlsanity.com/paper/2210.07373/) (2022)
- [Sequentially Controlled Text Generation](https://mlsanity.com/paper/2301.02299/) (2023)
- [Ontology-Free General-Domain Knowledge Graph-to-Text Generation Dataset Synthesis using Large Language Model](https://mlsanity.com/paper/2409.07088/) (2024)
- [Learning Extrapolative Sequence Transformations from Markov Chains](https://mlsanity.com/paper/2505.20251/) (2025)
- [Cross-Domain, Multi-Task Data-to-Text Generation without In-Domain Training Data](https://mlsanity.com/paper/2608.23391/) (2026)

## Abstract (arXiv)

We present a novel approach to data-to-text generation based on iterative text editing. Our approach maximizes the completeness and semantic accuracy of the output text while leveraging the abilities of recent pre-trained models for text editing (LaserTagger) and language modeling (GPT-2) to improve the text fluency. To this end, we first transform data items to text using trivial templates, and then we iteratively improve the resulting text by a neural model trained for the sentence fusion task. The output of the model is filtered by a simple heuristic and reranked with an off-the-shelf pre-trained language model. We evaluate our approach on two major data-to-text datasets (WebNLG, Cleaned E2E) and analyze its caveats and benefits. Furthermore, we show that our formulation of data-to-text generation opens up the possibility for zero-shot domain adaptation using a general-domain dataset for sentence fusion.