# Logical Natural Language Generation from Open-Domain Tables

arXiv: https://arxiv.org/abs/2004.10404 · HTML: https://mlsanity.com/paper/2004.10404/

## Key facts

- Cited by 90 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Apr 2020.

## Built on by (most cited first, 30 of 90)

- [Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey](https://mlsanity.com/paper/2111.01243/) (2021)
- [FOLIO: Natural Language Reasoning with First-Order Logic](https://mlsanity.com/paper/2209.00840/) (2022)
- [UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models](https://mlsanity.com/paper/2201.05966/) (2022)
- [FeTaQA: Free-form Table Question Answering](https://mlsanity.com/paper/2104.00369/) (2021)
- [Chart-to-Text: A Large-Scale Benchmark for Chart Summarization](https://mlsanity.com/paper/2203.06486/) (2022)
- [NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics](https://mlsanity.com/paper/2112.08726/) (2021)
- [HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generation](https://mlsanity.com/paper/2108.06712/) (2021)
- [Large Language Models are few(1)-shot Table Reasoners](https://mlsanity.com/paper/2210.06710/) (2022)
- [OpenCQA: Open-ended Question Answering with Charts](https://mlsanity.com/paper/2210.06628/) (2022)
- [From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Models](https://mlsanity.com/paper/2403.12027/) (2024)
- [Text-to-Table: A New Way of Information Extraction](https://mlsanity.com/paper/2109.02707/) (2021)
- [RobuT: A Systematic Study of Table QA Robustness Against Human-Annotated Adversarial Perturbations](https://mlsanity.com/paper/2306.14321/) (2023)
- [Table Pre-training: A Survey on Model Architectures, Pre-training Objectives, and Downstream Tasks](https://mlsanity.com/paper/2201.09745/) (2022)
- [Open Domain Question Answering with A Unified Knowledge Interface](https://mlsanity.com/paper/2110.08417/) (2021)
- [Robust (Controlled) Table-to-Text Generation with Structure-Aware Equivariance Learning](https://mlsanity.com/paper/2205.03972/) (2022)
- [ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples](https://mlsanity.com/paper/2210.12374/) (2022)
- [A Survey of Table Reasoning with Large Language Models](https://mlsanity.com/paper/2402.08259/) (2024)
- [TempTabQA: Temporal Question Answering for Semi-Structured Tables](https://mlsanity.com/paper/2311.08002/) (2023)
- [Retrieving Complex Tables with Multi-Granular Graph Representation Learning](https://mlsanity.com/paper/2105.01736/) (2021)
- [Exploring the Impact of Table-to-Text Methods on Augmenting LLM-based Question Answering with Domain Hybrid Data](https://mlsanity.com/paper/2402.12869/) (2024)
- [Logic-Consistency Text Generation from Semantic Parses](https://mlsanity.com/paper/2108.00577/) (2021)
- [Effective Distillation of Table-based Reasoning Ability from LLMs](https://mlsanity.com/paper/2309.13182/) (2023)
- [CABINET: Content Relevance based Noise Reduction for Table Question Answering](https://mlsanity.com/paper/2402.01155/) (2024)
- [TSQA: Tabular Scenario Based Question Answering](https://mlsanity.com/paper/2101.11429/) (2021)
- [LineCap: Line Charts for Data Visualization Captioning Models](https://mlsanity.com/paper/2207.07243/) (2022)
- [PLOG: Table-to-Logic Pretraining for Logical Table-to-Text Generation](https://mlsanity.com/paper/2205.12697/) (2022)
- [MVP: Multi-task Supervised Pre-training for Natural Language Generation](https://mlsanity.com/paper/2206.12131/) (2022)
- [A Sequence-to-Sequence&Set Model for Text-to-Table Generation](https://mlsanity.com/paper/2306.00137/) (2023)
- [Learning to Reason for Text Generation from Scientific Tables](https://mlsanity.com/paper/2104.08296/) (2021)
- [Summaries as Captions: Generating Figure Captions for Scientific Documents with Automated Text Summarization](https://mlsanity.com/paper/2302.12324/) (2023)

## Abstract (arXiv)

Neural natural language generation (NLG) models have recently shown remarkable progress in fluency and coherence. However, existing studies on neural NLG are primarily focused on surface-level realizations with limited emphasis on logical inference, an important aspect of human thinking and language. In this paper, we suggest a new NLG task where a model is tasked with generating natural language statements that can be logically entailed by the facts in an open-domain semi-structured table. To facilitate the study of the proposed logical NLG problem, we use the existing TabFact dataset citechen2019tabfact featured with a wide range of logical/symbolic inferences as our testbed, and propose new automatic metrics to evaluate the fidelity of generation models w.r.t. logical inference. The new task poses challenges to the existing monotonic generation frameworks due to the mismatch between sequence order and logical order. In our experiments, we comprehensively survey different generation architectures (LSTM, Transformer, Pre-Trained LM) trained with different algorithms (RL, Adversarial Training, Coarse-to-Fine) on the dataset and made following observations: 1) Pre-Trained LM can significantly boost both the fluency and logical fidelity metrics, 2) RL and Adversarial Training are trading fluency for fidelity, 3) Coarse-to-Fine generation can help partially alleviate the fidelity issue while maintaining high language fluency. The code and data are available at urlhttps://github.com/wenhuchen/LogicNLG.