# Neural Data-to-Text Generation via Jointly Learning the Segmentation and Correspondence

arXiv: https://arxiv.org/abs/2005.01096 · HTML: https://mlsanity.com/paper/2005.01096/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 May 2020.

## Built on by (most cited first, 25 of 25)

- [A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation](https://mlsanity.com/paper/2104.08704/) (2021)
- [Text-to-Table: A New Way of Information Extraction](https://mlsanity.com/paper/2109.02707/) (2021)
- [Controlling Hallucinations at Word Level in Data-to-Text Generation](https://mlsanity.com/paper/2102.02810/) (2021)
- [Does the Order of Training Samples Matter? Improving Neural Data-to-Text Generation with Curriculum Learning](https://mlsanity.com/paper/2102.03554/) (2021)
- [Sequence-to-Sequence Learning with Latent Neural Grammars](https://mlsanity.com/paper/2109.01135/) (2021)
- [Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methods](https://mlsanity.com/paper/2203.05227/) (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)
- [Improving Compositional Generalization with Self-Training for Data-to-Text Generation](https://mlsanity.com/paper/2110.08467/) (2021)
- [Neural Pipeline for Zero-Shot Data-to-Text Generation](https://mlsanity.com/paper/2203.16279/) (2022)
- [Learning Fine-grained Fact-Article Correspondence in Legal Cases](https://mlsanity.com/paper/2104.10726/) (2021)
- [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)
- [Attention Is Indeed All You Need: Semantically Attention-Guided Decoding for Data-to-Text NLG](https://mlsanity.com/paper/2109.07043/) (2021)
- [GenNI: Human-AI Collaboration for Data-Backed Text Generation](https://mlsanity.com/paper/2110.10185/) (2021)
- [CAB: Comprehensive Attention Benchmarking on Long Sequence Modeling](https://mlsanity.com/paper/2210.07661/) (2022)
- [Assessing "Implicit" Retrieval Robustness of Large Language Models](https://mlsanity.com/paper/2406.18134/) (2024)
- [AGGGEN: Ordering and Aggregating while Generating](https://mlsanity.com/paper/2106.05580/) (2021)
- [LOGEN: Few-shot Logical Knowledge-Conditioned Text Generation with Self-training](https://mlsanity.com/paper/2112.01404/) (2021)
- [A Systematic Review of Data-to-Text NLG](https://mlsanity.com/paper/2402.08496/) (2024)
- [Triples-to-isiXhosa (T2X): Addressing the Challenges of Low-Resource Agglutinative Data-to-Text Generation](https://mlsanity.com/paper/2403.07567/) (2024)
- [Learning to Express in Knowledge-Grounded Conversation](https://mlsanity.com/paper/2204.05805/) (2022)
- [Automatic Logical Forms improve fidelity in Table-to-Text generation](https://mlsanity.com/paper/2310.17279/) (2023)
- [Neural Sequence Segmentation as Determining the Leftmost Segments](https://mlsanity.com/paper/2104.07217/) (2021)
- [Ta-G-T: Subjectivity Capture in Table to Text Generation via RDF Graphs](https://mlsanity.com/paper/2507.19710/) (2025)

## Abstract (arXiv)

The neural attention model has achieved great success in data-to-text generation tasks. Though usually excelling at producing fluent text, it suffers from the problem of information missing, repetition and "hallucination". Due to the black-box nature of the neural attention architecture, avoiding these problems in a systematic way is non-trivial. To address this concern, we propose to explicitly segment target text into fragment units and align them with their data correspondences. The segmentation and correspondence are jointly learned as latent variables without any human annotations. We further impose a soft statistical constraint to regularize the segmental granularity. The resulting architecture maintains the same expressive power as neural attention models, while being able to generate fully interpretable outputs with several times less computational cost. On both E2E and WebNLG benchmarks, we show the proposed model consistently outperforms its neural attention counterparts.