# Learning to Select, Track, and Generate for Data-to-Text

arXiv: https://arxiv.org/abs/1907.09699 · HTML: https://mlsanity.com/paper/1907.09699/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jul 2019.

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

- [FeTaQA: Free-form Table Question Answering](https://mlsanity.com/paper/2104.00369/) (2021)
- [Conditional Generation with a Question-Answering Blueprint](https://mlsanity.com/paper/2207.00397/) (2022)
- [Data-to-text Generation with Macro Planning](https://mlsanity.com/paper/2102.02723/) (2021)
- [Data-to-text Generation with Variational Sequential Planning](https://mlsanity.com/paper/2202.13756/) (2022)
- [AutoChart: A Dataset for Chart-to-Text Generation Task](https://mlsanity.com/paper/2108.06897/) (2021)
- [Innovations in Neural Data-to-text Generation: A Survey](https://mlsanity.com/paper/2207.12571/) (2022)
- [Generation Challenges: Results of the Accuracy Evaluation Shared Task](https://mlsanity.com/paper/2108.05644/) (2021)
- [A Systematic Review of Data-to-Text NLG](https://mlsanity.com/paper/2402.08496/) (2024)
- [May the Force Be with Your Copy Mechanism: Enhanced Supervised-Copy Method for Natural Language Generation](https://mlsanity.com/paper/2112.10360/) (2021)
- [Ontology-Free General-Domain Knowledge Graph-to-Text Generation Dataset Synthesis using Large Language Model](https://mlsanity.com/paper/2409.07088/) (2024)
- [Few-Shot Table-to-Text Generation with Prompt Planning and Knowledge Memorization](https://mlsanity.com/paper/2302.04415/) (2023)
- [Adapting Knowledge for Few-shot Table-to-Text Generation](https://mlsanity.com/paper/2302.12468/) (2023)
- [Table Caption Generation in Scholarly Documents Leveraging Pre-trained Language Models](https://mlsanity.com/paper/2108.08111/) (2021)
- [Representing data in words: A context engineering approach](https://mlsanity.com/paper/2503.15509/) (2025)

## Abstract (arXiv)

We propose a data-to-text generation model with two modules, one for tracking and the other for text generation. Our tracking module selects and keeps track of salient information and memorizes which record has been mentioned. Our generation module generates a summary conditioned on the state of tracking module. Our model is considered to simulate the human-like writing process that gradually selects the information by determining the intermediate variables while writing the summary. In addition, we also explore the effectiveness of the writer information for generation. Experimental results show that our model outperforms existing models in all evaluation metrics even without writer information. Incorporating writer information further improves the performance, contributing to content planning and surface realization.