# Data-to-text Generation with Macro Planning

arXiv: https://arxiv.org/abs/2102.02723 · HTML: https://mlsanity.com/paper/2102.02723/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 73 references that are in the map.
- First posted on arXiv 4 Feb 2021.

## Builds on (most cited first, 30 of 33)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation](https://mlsanity.com/paper/1609.08144/) (2016)
- [Effective Approaches to Attention-based Neural Machine Translation](https://mlsanity.com/paper/1508.04025/) (2015)
- [Pointer Networks](https://mlsanity.com/paper/1506.03134/) (2015)
- [A Deep Reinforced Model for Abstractive Summarization](https://mlsanity.com/paper/1705.04304/) (2017)
- [The E2E Dataset: New Challenges For End-to-End Generation](https://mlsanity.com/paper/1706.09254/) (2017)
- [OpenNMT: Open-source Toolkit for Neural Machine Translation](https://mlsanity.com/paper/1709.03815/) (2017)
- [Challenges in Data-to-Document Generation](https://mlsanity.com/paper/1707.08052/) (2017)
- [Incorporating Copying Mechanism in Sequence-to-Sequence Learning](https://mlsanity.com/paper/1603.06393/) (2016)
- [Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation](https://mlsanity.com/paper/1703.09902/) (2017)
- [Do NLP Models Know Numbers? Probing Numeracy in Embeddings](https://mlsanity.com/paper/1909.07940/) (2019)
- [Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting](https://mlsanity.com/paper/1805.11080/) (2018)
- [Controllable Abstractive Summarization](https://mlsanity.com/paper/1711.05217/) (2017)
- [Data-to-Text Generation with Content Selection and Planning](https://mlsanity.com/paper/1809.00582/) (2018)
- [Controlling Output Length in Neural Encoder-Decoders](https://mlsanity.com/paper/1609.09552/) (2016)
- [Step-by-Step: Separating Planning from Realization in Neural Data-to-Text Generation](https://mlsanity.com/paper/1904.03396/) (2019)
- [Long and Diverse Text Generation with Planning-based Hierarchical Variational Model](https://mlsanity.com/paper/1908.06605/) (2019)
- [Sticking to the Facts: Confident Decoding for Faithful Data-to-Text Generation](https://mlsanity.com/paper/1910.08684/) (2019)
- [Neural data-to-text generation: A comparison between pipeline and end-to-end architectures](https://mlsanity.com/paper/1908.09022/) (2019)
- [Data-to-text Generation with Entity Modeling](https://mlsanity.com/paper/1906.03221/) (2019)
- [Pointing the Unknown Words](https://mlsanity.com/paper/1603.08148/) (2016)
- [Simple and Effective Noisy Channel Modeling for Neural Machine Translation](https://mlsanity.com/paper/1908.05731/) (2019)
- [What to talk about and how? Selective Generation using LSTMs with Coarse-to-Fine Alignment](https://mlsanity.com/paper/1509.00838/) (2015)
- [A Hierarchical Model for Data-to-Text Generation](https://mlsanity.com/paper/1912.10011/) (2019)
- [Table-to-Text Generation with Effective Hierarchical Encoder on Three Dimensions (Row, Column and Time)](https://mlsanity.com/paper/1909.02304/) (2019)
- [Learning to Select, Track, and Generate for Data-to-Text](https://mlsanity.com/paper/1907.09699/) (2019)
- [Scalable Micro-planned Generation of Discourse from Structured Data](https://mlsanity.com/paper/1810.02889/) (2018)

## Built on by (most cited first, 30 of 34)

- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Conditional Generation with a Question-Answering Blueprint](https://mlsanity.com/paper/2207.00397/) (2022)
- [Automatic Generation of Socratic Subquestions for Teaching Math Word Problems](https://mlsanity.com/paper/2211.12835/) (2022)
- [IndicNLG Benchmark: Multilingual Datasets for Diverse NLG Tasks in Indic Languages](https://mlsanity.com/paper/2203.05437/) (2022)
- [GEMv2: Multilingual NLG Benchmarking in a Single Line of Code](https://mlsanity.com/paper/2206.11249/) (2022)
- [Long Text and Multi-Table Summarization: Dataset and Method](https://mlsanity.com/paper/2302.03815/) (2023)
- [Data-to-text Generation with Variational Sequential Planning](https://mlsanity.com/paper/2202.13756/) (2022)
- [Beyond Traditional Benchmarks: Analyzing Behaviors of Open LLMs on Data-to-Text Generation](https://mlsanity.com/paper/2401.10186/) (2024)
- [LitLLMs, LLMs for Literature Review: Are we there yet?](https://mlsanity.com/paper/2412.15249/) (2024)
- [Innovations in Neural Data-to-text Generation: A Survey](https://mlsanity.com/paper/2207.12571/) (2022)
- [TaTa: A Multilingual Table-to-Text Dataset for African Languages](https://mlsanity.com/paper/2211.00142/) (2022)
- [Less is More: Mitigate Spurious Correlations for Open-Domain Dialogue Response Generation Models by Causal Discovery](https://mlsanity.com/paper/2303.01962/) (2023)
- [MetaSumPerceiver: Multimodal Multi-Document Evidence Summarization for Fact-Checking](https://mlsanity.com/paper/2407.13089/) (2024)
- [Structsum Generation for Faster Text Comprehension](https://mlsanity.com/paper/2401.06837/) (2024)
- [μPLAN: Summarizing using a Content Plan as Cross-Lingual Bridge](https://mlsanity.com/paper/2305.14205/) (2023)
- [Think While You Write: Hypothesis Verification Promotes Faithful Knowledge-to-Text Generation](https://mlsanity.com/paper/2311.09467/) (2023)
- [Event Transition Planning for Open-ended Text Generation](https://mlsanity.com/paper/2204.09453/) (2022)
- [A Systematic Review of Data-to-Text NLG](https://mlsanity.com/paper/2402.08496/) (2024)
- [CoPERLex: Content Planning with Event-based Representations for Legal Case Summarization](https://mlsanity.com/paper/2501.14112/) (2025)
- [Triples-to-isiXhosa (T2X): Addressing the Challenges of Low-Resource Agglutinative Data-to-Text Generation](https://mlsanity.com/paper/2403.07567/) (2024)
- [Enhancing Commentary Strategies for Imperfect Information Card Games: A Study of Large Language Models in Guandan Commentary](https://mlsanity.com/paper/2406.17807/) (2024)
- [Little Red Riding Hood Goes Around the Globe:Crosslingual Story Planning and Generation with Large Language Models](https://mlsanity.com/paper/2212.10471/) (2022)
- [Plan-then-Seam: Towards Efficient Table-to-Text Generation](https://mlsanity.com/paper/2302.05138/) (2023)
- [An Extensive Evaluation of Factual Consistency in Large Language Models for Data-to-Text Generation](https://mlsanity.com/paper/2411.19203/) (2024)
- [Table Caption Generation in Scholarly Documents Leveraging Pre-trained Language Models](https://mlsanity.com/paper/2108.08111/) (2021)
- [Medical Scientific Table-to-Text Generation with Human-in-the-Loop under the Data Sparsity Constraint](https://mlsanity.com/paper/2205.12368/) (2022)
- [Facts-and-Feelings: Capturing both Objectivity and Subjectivity in Table-to-Text Generation](https://mlsanity.com/paper/2406.10560/) (2024)
- [Impact of Model Size on Fine-tuned LLM Performance in Data-to-Text Generation: A State-of-the-Art Investigation](https://mlsanity.com/paper/2407.14088/) (2024)
- [Alternatives To Next Token Prediction In Text Generation -- A Survey](https://mlsanity.com/paper/2509.24435/) (2025)
- [Illocutionary Explanation Planning for Source-Faithful Explanations in Retrieval-Augmented Language Models](https://mlsanity.com/paper/2604.06211/) (2026)

## Abstract (arXiv)

Recent approaches to data-to-text generation have adopted the very successful encoder-decoder architecture or variants thereof. These models generate text which is fluent (but often imprecise) and perform quite poorly at selecting appropriate content and ordering it coherently. To overcome some of these issues, we propose a neural model with a macro planning stage followed by a generation stage reminiscent of traditional methods which embrace separate modules for planning and surface realization. Macro plans represent high level organization of important content such as entities, events and their interactions; they are learnt from data and given as input to the generator. Extensive experiments on two data-to-text benchmarks (RotoWire and MLB) show that our approach outperforms competitive baselines in terms of automatic and human evaluation.