# Have Your Text and Use It Too! End-to-End Neural Data-to-Text Generation with Semantic Fidelity

arXiv: https://arxiv.org/abs/2004.06577 · HTML: https://mlsanity.com/paper/2004.06577/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Apr 2020.

## Built on by (most cited first, 30 of 35)

- [Pretrained Language Models for Text Generation: A Survey](https://mlsanity.com/paper/2201.05273/) (2022)
- [Machine Generated Text: A Comprehensive Survey of Threat Models and Detection Methods](https://mlsanity.com/paper/2210.07321/) (2022)
- [Structural Adapters in Pretrained Language Models for AMR-to-text Generation](https://mlsanity.com/paper/2103.09120/) (2021)
- [RuCoLA: Russian Corpus of Linguistic Acceptability](https://mlsanity.com/paper/2210.12814/) (2022)
- [Control Prefixes for Parameter-Efficient Text Generation](https://mlsanity.com/paper/2110.08329/) (2021)
- [Logic-Consistency Text Generation from Semantic Parses](https://mlsanity.com/paper/2108.00577/) (2021)
- [Neural Pipeline for Zero-Shot Data-to-Text Generation](https://mlsanity.com/paper/2203.16279/) (2022)
- [Evaluating Generative Models for Graph-to-Text Generation](https://mlsanity.com/paper/2307.14712/) (2023)
- [ASDOT: Any-Shot Data-to-Text Generation with Pretrained Language Models](https://mlsanity.com/paper/2210.04325/) (2022)
- [Jointly Improving Language Understanding and Generation with Quality-Weighted Weak Supervision of Automatic Labeling](https://mlsanity.com/paper/2102.03551/) (2021)
- [Stage-wise Fine-tuning for Graph-to-Text Generation](https://mlsanity.com/paper/2105.08021/) (2021)
- [DYPLOC: Dynamic Planning of Content Using Mixed Language Models for Text Generation](https://mlsanity.com/paper/2106.00791/) (2021)
- [Attention Is Indeed All You Need: Semantically Attention-Guided Decoding for Data-to-Text NLG](https://mlsanity.com/paper/2109.07043/) (2021)
- [Innovations in Neural Data-to-text Generation: A Survey](https://mlsanity.com/paper/2207.12571/) (2022)
- [What Makes Data-to-Text Generation Hard for Pretrained Language Models?](https://mlsanity.com/paper/2205.11505/) (2022)
- [Critic-Driven Decoding for Mitigating Hallucinations in Data-to-text Generation](https://mlsanity.com/paper/2310.16964/) (2023)
- [Mind the Labels: Describing Relations in Knowledge Graphs With Pretrained Models](https://mlsanity.com/paper/2210.07373/) (2022)
- [The Pitfalls of Defining Hallucination](https://mlsanity.com/paper/2401.07897/) (2024)
- [WDV: A Broad Data Verbalisation Dataset Built from Wikidata](https://mlsanity.com/paper/2205.02627/) (2022)
- [Controllable Generation of Dialogue Acts for Dialogue Systems via Few-Shot Response Generation and Ranking](https://mlsanity.com/paper/2307.14440/) (2023)
- [A Systematic Review of Data-to-Text NLG](https://mlsanity.com/paper/2402.08496/) (2024)
- [Smelting Gold and Silver for Improved Multilingual AMR-to-Text Generation](https://mlsanity.com/paper/2109.03808/) (2021)
- [WeaSuL: Weakly Supervised Dialogue Policy Learning: Reward Estimation for Multi-turn Dialogue](https://mlsanity.com/paper/2108.01487/) (2021)
- [You Can Generate It Again: Data-to-Text Generation with Verification and Correction Prompting](https://mlsanity.com/paper/2306.15933/) (2023)
- [Automatic Logical Forms improve fidelity in Table-to-Text generation](https://mlsanity.com/paper/2310.17279/) (2023)
- [GraSAME: Injecting Token-Level Structural Information to Pretrained Language Models via Graph-guided Self-Attention Mechanism](https://mlsanity.com/paper/2404.06911/) (2024)
- [R2D2: Relational Text Decoding with Transformers](https://mlsanity.com/paper/2105.04645/) (2021)
- [Schema-Guided Semantic Accuracy: Faithfulness in Task-Oriented Dialogue Response Generation](https://mlsanity.com/paper/2301.12568/) (2023)
- [Knowledge Graph for NLG in the context of conversational agents](https://mlsanity.com/paper/2307.01548/) (2023)
- [An xAI Approach for Data-to-Text Processing with ASP](https://mlsanity.com/paper/2308.15898/) (2023)

## Abstract (arXiv)

End-to-end neural data-to-text (D2T) generation has recently emerged as an alternative to pipeline-based architectures. However, it has faced challenges in generalizing to new domains and generating semantically consistent text. In this work, we present DataTuner, a neural, end-to-end data-to-text generation system that makes minimal assumptions about the data representation and the target domain. We take a two-stage generation-reranking approach, combining a fine-tuned language model with a semantic fidelity classifier. Each of our components is learnt end-to-end without the need for dataset-specific heuristics, entity delexicalization, or post-processing. We show that DataTuner achieves state of the art results on the automated metrics across four major D2T datasets (LDC2017T10, WebNLG, ViGGO, and Cleaned E2E), with a fluency assessed by human annotators nearing or exceeding the human-written reference texts. We further demonstrate that the model-based semantic fidelity scorer in DataTuner is a better assessment tool compared to traditional, heuristic-based measures. Our generated text has a significantly better semantic fidelity than the state of the art across all four datasets