Lune

ACL Findings2023

A Sequence-to-Sequence&Set Model for Text-to-Table Generation

Tong Li, Zhihao Wang, Liangying Shao, Xuling Zheng, Xiaoli Wang, Jinsong Su

Abstract

Recently, the text-to-table generation task has attracted increasing attention due to its wide applications. In this aspect, the dominant model (Wu et al., 2022) formalizes this task as a sequence-to-sequence generation task and serializes each table into a token sequence during training by concatenating all rows in a topdown order. However, it suffers from two serious defects: 1) the predefined order introduces a wrong bias during training, which highly penalizes shifts in the order between rows; 2) the error propagation problem becomes serious when the model outputs a long token sequence. In this paper, we first conduct a preliminary study to demonstrate the generation of most rows is order-insensitive. Furthermore, we propose a novel sequence-to-sequence&set text-to-table generation model. Specifically, in addition to a text encoder encoding the input text, our model is equipped with a table header generator to first output a table header, i.e., the first row of the table, in the manner of sequence generation. Then we use a table body generator with learnable row embeddings and column embeddings to generate a set of table body rows in parallel. Particularly, to deal with the issue that there is no correspondence between each generated table body row and target during training, we propose a target assignment strategy based on the bipartite matching between the first cells of generated table body rows and targets. Experiment results show that our model significantly surpasses the baselines, achieving state-of-the-art performance on commonlyused datasets. 1

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.

4 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Text-Tuple-Table: Towards Information Integration in Text-to-Table Generation via Global Tuple Extraction cites STRUCTSUM Generation for Faster Text Comprehension
  • TST: A Schema-Based Top-Down and Dynamic-Aware Agent of Text-to-Table Tasks cites Text-Tuple-Table: Towards Information Integration in Text-to-Table Generation via Global Tuple Extraction
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers4

  1. arXiv2Table: Toward Realistic Benchmarking and Evaluation for LLM-Based Literature-Review Table GenerationWeiqi Wang, Jiefu Ou, Yangqiu Song, Benjamin Van Durme et al.ACL 2026 · 8 citations
  2. Text-Tuple-Table: Towards Information Integration in Text-to-Table Generation via Global Tuple ExtractionZheye Deng, Chunkit Chan, Weiqi Wang, Yuxi Sun et al.EMNLP 2024 · 2 citations
  3. STRUCTSUM Generation for Faster Text ComprehensionParag Jain, Andreea Marzoca, Francesco PiccinnoACL 2024 · 2 citations
  4. TST: A Schema-Based Top-Down and Dynamic-Aware Agent of Text-to-Table TasksPeiwen Jiang, Haitong Jiang, Ruhui Ma, Yvonne Jie Chen et al.ACL 2025

Builds on12

  1. Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order SensitivityYao Lu, Max Bartolo, Alastair Moore, Sebastian Riedel et al.ACL 2022 · 1,494 citations
  2. BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and ComprehensionMike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad et al.ACL 2020 · 1,224 citations
  3. Effective Modeling of Encoder-Decoder Architecture for Joint Entity and Relation ExtractionTapas Nayak, Hwee Tou NgAAAI 2020 · 272 citations
  4. Neural Machine Translation with Byte-Level SubwordsChanghan Wang, Kyunghyun Cho, Jiatao GuAAAI 2020 · 213 citations
  5. Logical Natural Language Generation from Open-Domain TablesWenhu Chen, Jianshu Chen, Yu Su, Zhiyu Chen et al.ACL 2020 · 116 citations

Related papers

  1. Text-to-Table: A New Way of Information ExtractionXueqing Wu, Jiacheng Zhang, Hang LiACL 2022
  2. Structure-Aware Pre-Training for Table-to-Text GenerationXinyu Xing, Xiaojun WanACL Findings 2021 · 20 citations
  3. Attend, Memorize and Generate: Towards Faithful Table-to-Text Generation in Few ShotsWenting Zhao, Ye Liu, Yao Wan, Philip S. YuEMNLP Findings 2021 · 12 citations
  4. A Table-to-Text Framework with Heterogeneous Multidominance Attention and Self-Evaluated Multi-Pass DeliberationXi Chen, Xinjiang Lu, Haoran Xin, Wenjun Peng et al.EMNLP Findings 2023 · 3 citations
  5. Table-To-Text generation and pre-training with TabT5Ewa Andrejczuk, Julian Martin Eisenschlos, Francesco Piccinno, Syrine Krichene et al.EMNLP Findings 2022 · 24 citations
Dusk over the sea between two cliffs drawn in fine vertical lines