Data-to-Text Generation

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

26 leaderboard tables shown for this task, 26 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 26 until expanded.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

24 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

3 subtasks in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 112 papers with code (219 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Language Models are Unsupervised Multitask Learners
  14 Feb 2019 21 repositories listed
  Natural language processing tasks, such as question answering, machine translation, reading comprehension, and summarization, are typically approached with supervised learning on taskspecific datasets.
• MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance
  5 Sep 2019 4 repositories listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  A robust evaluation metric has a profound impact on the development of text generation systems.
• Challenges in Data-to-Document Generation
  25 Jul 2017 4 repositories listed
  Recent neural models have shown significant progress on the problem of generating short descriptive texts conditioned on a small number of database records.
• Investigating Pretrained Language Models for Graph-to-Text Generation
  16 Jul 2020 3 repositories listed Syntology ran 2 of 12 samples · 10 unverified
  We show that the PLMs BART and T5 achieve new state-of-the-art results and that task-adaptive pretraining strategies improve their performance even further.
• Triples-to-isiXhosa (T2X): Addressing the Challenges of Low-Resource Agglutinative Data-to-Text Generation
  12 Mar 2024 2 repositories listed
  In this paper we tackle data-to-text for isiXhosa, which is low-resource and agglutinative.
• TaTa: A Multilingual Table-to-Text Dataset for African Languages
  31 Oct 2022 2 repositories listed
  To address this lack of data, we create Table-to-Text in African languages (TaTa), the first large multilingual table-to-text dataset with a focus on African languages.
• CoNT: Contrastive Neural Text Generation
  29 May 2022 2 repositories listed
  We validate CoNT on five generation tasks with ten benchmarks, including machine translation, summarization, code comment generation, data-to-text generation and commonsense generation.
• Chart-to-Text: A Large-Scale Benchmark for Chart Summarization
  12 Mar 2022 2 repositories listed Syntology ran 5 of 5 samples · 0 unverified · 5 pointer-only (licence)
  We also introduce a number of state-of-the-art neural models as baselines that utilize image captioning and data-to-text generation techniques to tackle two problem variations: one assumes the underlying data table of…
• Control Prefixes for Parameter-Efficient Text Generation
  15 Oct 2021 2 repositories listed
  Prefix-tuning is a powerful lightweight technique for adapting a large pre-trained language model to a downstream application.
• Plan-then-Generate: Controlled Data-to-Text Generation via Planning
  31 Aug 2021 2 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  However, the lack of ability of neural models to control the structure of generated output can be limiting in certain real-world applications.
• Learning to Reason for Text Generation from Scientific Tables
  16 Apr 2021 2 repositories listed
  In this paper, we introduce SciGen, a new challenge dataset for the task of reasoning-aware data-to-text generation consisting of tables from scientific articles and their corresponding descriptions.
• Data-QuestEval: A Referenceless Metric for Data-to-Text Semantic Evaluation
  15 Apr 2021 2 repositories listed Syntology ran 2 of 3 samples · 1 unverified
  QuestEval is a reference-less metric used in text-to-text tasks, that compares the generated summaries directly to the source text, by automatically asking and answering questions.
• Text-to-Text Pre-Training for Data-to-Text Tasks
  21 May 2020 2 repositories listed
  We study the pre-train + fine-tune strategy for data-to-text tasks.
• Few-shot Natural Language Generation for Task-Oriented Dialog
  27 Feb 2020 2 repositories listed
  It is pre-trained on a large set of annotated NLG corpus to acquire the controllable generation ability, and fine-tuned with only a few domain-specific labels to adapt to new domains.
• Long and Diverse Text Generation with Planning-based Hierarchical Variational Model
  19 Aug 2019 2 repositories listed
  Existing neural methods for data-to-text generation are still struggling to produce long and diverse texts: they are insufficient to model input data dynamically during generation, to capture inter-sentence coherence,…
• Learning to Select, Track, and Generate for Data-to-Text
  23 Jul 2019 2 repositories listed
  We propose a data-to-text generation model with two modules, one for tracking and the other for text generation.
• Data-to-text Generation with Entity Modeling
  7 Jun 2019 2 repositories listed Syntology ran 1 of 2 samples · 1 unverified
  Recent approaches to data-to-text generation have shown great promise thanks to the use of large-scale datasets and the application of neural network architectures which are trained end-to-end.
• Semantically Conditioned Dialog Response Generation via Hierarchical Disentangled Self-Attention
  30 May 2019 2 repositories listed Syntology ran 2 of 3 samples · 1 unverified · 2 pointer-only (licence)
  Semantically controlled neural response generation on limited-domain has achieved great performance.
• Pragmatically Informative Text Generation
  2 Apr 2019 2 repositories listed
  We improve the informativeness of models for conditional text generation using techniques from computational pragmatics.
• Handling Rare Items in Data-to-Text Generation
  1 Nov 2018 2 repositories listed
  Neural approaches to data-to-text generation generally handle rare input items using either delexicalisation or a copy mechanism.
• Deep Graph Convolutional Encoders for Structured Data to Text Generation
  23 Oct 2018 2 repositories listed Syntology ran 1 of 3 samples · 2 unverified
  Most previous work on neural text generation from graph-structured data relies on standard sequence-to-sequence methods.
• Data-to-Text Generation with Content Selection and Planning
  3 Sep 2018 2 repositories listed
  Recent advances in data-to-text generation have led to the use of large-scale datasets and neural network models which are trained end-to-end, without explicitly modeling what to say and in what order.
• The E2E Dataset: New Challenges For End-to-End Generation
  28 Jun 2017 2 repositories listed
  This paper describes the E2E data, a new dataset for training end-to-end, data-driven natural language generation systems in the restaurant domain, which is ten times bigger than existing, frequently used datasets in…
• Ontology-Free General-Domain Knowledge Graph-to-Text Generation Dataset Synthesis using Large Language Model
  11 Sep 2024 1 repository listed Syntology ran 5 of 7 samples · 2 unverified · 7 pointer-only (licence)
  Our method proves to be a scalable and effective solution for generating high-quality G2T data, significantly advancing the field of G2T generation.
• SPOR: A Comprehensive and Practical Evaluation Method for Compositional Generalization in Data-to-Text Generation
  17 May 2024 1 repository listed Syntology ran 5 of 9 samples · 4 unverified
  Our work shows the necessity for comprehensive research on different manifestations of compositional generalization in data-to-text generation and provides a framework for evaluation.
• Bridging the Gap between Different Vocabularies for LLM Ensemble
  15 Apr 2024 1 repository listed Syntology ran 4 of 6 samples · 2 unverified · 6 pointer-only (licence)
  Ensembling different large language models (LLMs) to unleash their complementary potential and harness their individual strengths is highly valuable.
• Prompting for Numerical Sequences: A Case Study on Market Comment Generation
  3 Apr 2024 1 repository listed
  Large language models (LLMs) have been applied to a wide range of data-to-text generation tasks, including tables, graphs, and time-series numerical data-to-text settings.
• High-quality Data-to-Text Generation for Severely Under-Resourced Languages with Out-of-the-box Large Language Models
  19 Feb 2024 1 repository listed
  The performance of NLP methods for severely under-resourced languages cannot currently hope to match the state of the art in NLP methods for well resourced languages.
• Self-training from Self-memory in Data-to-text Generation
  19 Jan 2024 1 repository listed
  The quality of self-memory is validated by two models, data-to-text (D2T) and text-to-data (T2D), by two pre-defined conditions: (1) the appearance of all source values in the outputs of the D2T model and (2) the…
• Unifying Structured Data as Graph for Data-to-Text Pre-Training
  2 Jan 2024 1 repository listed
  In this paper, we unify different types of structured data (i.

Syntology lines on 11 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.