Lune

ACL Findings2023

SORTIE: Dependency-Aware Symbolic Reasoning for Logical Data-to-text Generation

Xueliang Zhao, Tingchen Fu, Lemao Liu, Lingpeng Kong, Shuming Shi, Rui Yan

Abstract

Logical data-to-text generation is a representative task in measuring the capabilities of both language generation and complex reasoning. Despite the introduction of reasoning skills in generation, existing works still rely on neural language models to output the final table description. However, due to the inefficacy of neural language models in complex reasoning, these methods inevitably have difficulty working out key entities in the description and might produce unfaithful descriptions. To alleviate these issues, we propose a dependencyaware symbolic reasoning framework that reasons out each entity in the table description with our designed table-compatible programming language. To figure out the dependency relationship among entities, we devise an entity scheduling mechanism to determine the order of programme synthesis such that the reasoning of an entity only relies on other "resolved" entities. Experiments on three datasets and three backbones show that ours outperforms previous methods not only in surfacelevel fidelity but also in logical fidelity. Notably, the proposed framework enhances GPT-2, BART and T5 with an absolute improvement of 5.7% ∼ 11.5% on SP-Acc.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • PAL: Program-aided Language Models cites Neural Module Networks for Reasoning over Text
  • PAL: Program-aided Language Models cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on19

  1. Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
  2. PAL: Program-aided Language ModelsLuyu Gao, Aman Madaan, Shuyan Zhou, Uri Alon et al.ICML 2023 · 700 citations
  3. TabFact: A Large-scale Dataset for Table-based Fact VerificationWenhu Chen, Hongmin Wang, Jianshu Chen, Yunkai Zhang et al.ICLR 2020 · 674 citations
  4. Self-Adaptive Training: beyond Empirical Risk MinimizationLang Huang, Chao Zhang, Hongyang ZhangNeurIPS 2020 · 256 citations
  5. Neural Module Networks for Reasoning over TextNitish Gupta, Kevin Lin, Dan Roth, Sameer Singh et al.ICLR 2020 · 134 citations

Related papers

  1. Toward a Unified Framework for Unsupervised Complex Tabular ReasoningZhenyu Li, Xiuxing Li, Zhichao Duan, Bowen Dong et al.ICDE 2023 · 4 citations
  2. Investigating the Robustness of Natural Language Generation from Logical Forms via Counterfactual SamplesChengyuan Liu, Leilei Gan, Kun Kuang, Fei WuEMNLP 2022 · 2 citations
  3. PLOG: Table-to-Logic Pretraining for Logical Table-to-Text GenerationAo Liu, Haoyu Dong, Naoaki Okazaki, Shi Han et al.EMNLP 2022 · 15 citations
  4. NormTab: Improving Symbolic Reasoning in LLMs Through Tabular Data NormalizationMd Mahadi Hasan Nahid, Davood RafieiEMNLP Findings 2024 · 6 citations
  5. Probing How Scalable Table Data Enhances General Long-Context ReasoningHuaibing Xie, Guoliang Zhao, Yang Liu, Shihan Dou et al.ICML 2026
Dusk over the sea between two cliffs drawn in fine vertical lines