# Key Fact as Pivot: A Two-Stage Model for Low Resource Table-to-Text Generation

arXiv: https://arxiv.org/abs/1908.03067 · HTML: https://mlsanity.com/paper/1908.03067/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Aug 2019.

## Built on by (most cited first, 20 of 20)

- [A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation](https://mlsanity.com/paper/2104.08704/) (2021)
- [Plan-then-Generate: Controlled Data-to-Text Generation via Planning](https://mlsanity.com/paper/2108.13740/) (2021)
- [Robust (Controlled) Table-to-Text Generation with Structure-Aware Equivariance Learning](https://mlsanity.com/paper/2205.03972/) (2022)
- [Towards Faithfulness in Open Domain Table-to-text Generation from an Entity-centric View](https://mlsanity.com/paper/2102.08585/) (2021)
- [Neural Data-to-Text Generation with LM-based Text Augmentation](https://mlsanity.com/paper/2102.03556/) (2021)
- [Sketch and Refine: Towards Faithful and Informative Table-to-Text Generation](https://mlsanity.com/paper/2105.14778/) (2021)
- [Few-Shot Table-to-Text Generation with Prototype Memory](https://mlsanity.com/paper/2108.12516/) (2021)
- [LANISTR: Multimodal Learning from Structured and Unstructured Data](https://mlsanity.com/paper/2305.16556/) (2023)
- [What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Data](https://mlsanity.com/paper/2106.06410/) (2021)
- [Innovations in Neural Data-to-text Generation: A Survey](https://mlsanity.com/paper/2207.12571/) (2022)
- [Attend, Memorize and Generate: Towards Faithful Table-to-Text Generation in Few Shots](https://mlsanity.com/paper/2203.00732/) (2022)
- [Few-Shot Table-to-Text Generation with Prefix-Controlled Generator](https://mlsanity.com/paper/2208.10709/) (2022)
- [Few-Shot Table-to-Text Generation with Prompt Planning and Knowledge Memorization](https://mlsanity.com/paper/2302.04415/) (2023)
- [Plan-then-Seam: Towards Efficient Table-to-Text Generation](https://mlsanity.com/paper/2302.05138/) (2023)
- [Adapting Knowledge for Few-shot Table-to-Text Generation](https://mlsanity.com/paper/2302.12468/) (2023)
- [High-Resource Methodological Bias in Low-Resource Investigations](https://mlsanity.com/paper/2211.07534/) (2022)
- [IFDID: Information Filter upon Diversity-Improved Decoding for Diversity-Faithfulness Tradeoff in NLG](https://mlsanity.com/paper/2210.13829/) (2022)
- [Self-training from Self-memory in Data-to-text Generation](https://mlsanity.com/paper/2401.10567/) (2024)
- [TrICy: Trigger-guided Data-to-text Generation with Intent aware Attention-Copy](https://mlsanity.com/paper/2402.01714/) (2024)
- [Data Transformation Strategies to Remove Heterogeneity](https://mlsanity.com/paper/2507.12677/) (2025)

## Abstract (arXiv)

Table-to-text generation aims to translate the structured data into the unstructured text. Most existing methods adopt the encoder-decoder framework to learn the transformation, which requires large-scale training samples. However, the lack of large parallel data is a major practical problem for many domains. In this work, we consider the scenario of low resource table-to-text generation, where only limited parallel data is available. We propose a novel model to separate the generation into two stages: key fact prediction and surface realization. It first predicts the key facts from the tables, and then generates the text with the key facts. The training of key fact prediction needs much fewer annotated data, while surface realization can be trained with pseudo parallel corpus. We evaluate our model on a biography generation dataset. Our model can achieve 27.34 BLEU score with only 1,000 parallel data, while the baseline model only obtain the performance of 9.71 BLEU score.