EMNLP Findings2020
Logic2Text: High-Fidelity Natural Language Generation from Logical Forms
Zhiyu Chen, Wenhu Chen, Hanwen Zha, Xiyou Zhou, Yunkai Zhang, Sairam Sundaresan, William Yang Wang
Abstract
Previous studies on Natural Language Generation (NLG) from structured data have primarily focused on surface-level descriptions of record sequences. However, for complex structured data, e.g., multi-row tables, it is often desirable for an NLG system to describe interesting facts from logical inferences across records. If only provided with the table, it is hard for existing models to produce controllable and high-fidelity logical generations. In this work, we formulate highfidelity NLG as generation from logical forms in order to obtain controllable and faithful generations. We present a new large-scale dataset, LOGIC2TEXT, with 10,753 descriptions involving common logic types paired with the underlying logical forms.
The logical forms show diversified graph structure of free schema, which pose great challenges on the model's ability to understand the semantics. We experiment on (1) Fullysupervised training with the full datasets, and (2) Few-shot setting, provided with hundreds of paired examples; We compare several popular generation models and analyze their performances. We hope our dataset can encourage research towards building an advanced NLG system capable of natural, faithful, and human-like generation. The dataset and code is available at https://github. com/czyssrs/Logic2Text.
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.
11 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- TSQA: Tabular Scenario Based Question Answering cites TabFact: A Large-scale Dataset for Table-based Fact Verification
- TSQA: Tabular Scenario Based Question Answering cites Logical Natural Language Generation from Open-Domain Tables
- ToTTo: A Controlled Table-To-Text Generation Dataset cites TabFact: A Large-scale Dataset for Table-based Fact Verification
- ToTTo: A Controlled Table-To-Text Generation Dataset cites Logical Natural Language Generation from Open-Domain Tables
- CABINET: Content Relevance-based Noise Reduction for Table Question Answering cites TabFact: A Large-scale Dataset for Table-based Fact Verification
- CABINET: Content Relevance-based Noise Reduction for Table Question Answering cites ToTTo: A Controlled Table-To-Text Generation Dataset
- CABINET: Content Relevance-based Noise Reduction for Table Question Answering cites Logical Natural Language Generation from Open-Domain Tables
- PLOG: Table-to-Logic Pretraining for Logical Table-to-Text Generation cites TabFact: A Large-scale Dataset for Table-based Fact Verification
- PLOG: Table-to-Logic Pretraining for Logical Table-to-Text Generation cites ToTTo: A Controlled Table-To-Text Generation Dataset
- PLOG: Table-to-Logic Pretraining for Logical Table-to-Text Generation cites Logical Natural Language Generation from Open-Domain Tables
- ReTAG: Reasoning Aware Table to Analytic Text Generation cites TabFact: A Large-scale Dataset for Table-based Fact Verification
- ReTAG: Reasoning Aware Table to Analytic Text Generation cites ToTTo: A Controlled Table-To-Text Generation Dataset
- ReTAG: Reasoning Aware Table to Analytic Text Generation cites Logical Natural Language Generation from Open-Domain Tables
- Logical Natural Language Generation from Open-Domain Tables cites TabFact: A Large-scale Dataset for Table-based Fact Verification
Cited by top-tier papers11
- TSQA: Tabular Scenario Based Question AnsweringXiao Li, Yawei Sun, Gong ChengAAAI 2021 · 37 citations
- CABINET: Content Relevance-based Noise Reduction for Table Question AnsweringSohan Patnaik, Heril Changwal, Milan Aggarwal, Sumit Bhatia et al.ICLR 2024 · 34 citations
- PLOG: Table-to-Logic Pretraining for Logical Table-to-Text GenerationAo Liu, Haoyu Dong, Naoaki Okazaki, Shi Han et al.EMNLP 2022 · 15 citations
- Pointwise Mutual Information Based Metric and Decoding Strategy for Faithful Generation in Document Grounded DialogsYatin Nandwani, Vineet Kumar, Dinesh Raghu, Sachindra Joshi et al.EMNLP 2023 · 4 citations
- ReTAG: Reasoning Aware Table to Analytic Text GenerationDeepanway Ghosal, Preksha Nema, Aravindan RaghuveerEMNLP 2023 · 3 citations
Builds on3
- TabFact: A Large-scale Dataset for Table-based Fact VerificationWenhu Chen, Hongmin Wang, Jianshu Chen, Yunkai Zhang et al.ICLR 2020 · 674 citations
- Logical Natural Language Generation from Open-Domain TablesWenhu Chen, Jianshu Chen, Yu Su, Zhiyu Chen et al.ACL 2020 · 116 citations
- ToTTo: A Controlled Table-To-Text Generation DatasetAnkur P. Parikh, Xuezhi Wang, Sebastian Gehrmann, Manaal Faruqui et al.EMNLP 2020 · 69 citations
Related papers
- Investigating the Robustness of Natural Language Generation from Logical Forms via Counterfactual SamplesChengyuan Liu, Leilei Gan, Kun Kuang, Fei WuEMNLP 2022 · 2 citations
- Natural Language Inference in Context - Investigating Contextual Reasoning over Long TextsHanmeng Liu, Leyang Cui, Jian Liu, Yue ZhangAAAI 2021 · 57 citations
- SciTables : A Dataset and Evaluation Framework for Complex Table-to-Text GenerationMehrnoush Alizade, Tengrui Kong, Suman Kalyan MaityVLDB 2026
- TWT: Table with Written Text for Controlled Data-to-Text GenerationTongliang Li, Lei Fang, Jian-Guang Lou, Zhoujun LiEMNLP Findings 2021 · 12 citations
- NL2TL: Transforming Natural Languages to Temporal Logics using Large Language ModelsYongchao Chen, Rujul Gandhi, Yang Zhang, Chuchu FanEMNLP 2023 · 48 citations
