Papers › RecipeNLG: A Cooking Recipes Dataset for Semi-Structured Text Generation

RecipeNLG: A Cooking Recipes Dataset for Semi-Structured Text Generation

15 Dec 2020archive 2025-07-28

Michał Bień, Michał Gilski, Martyna Maciejewska, Wojciech Taisner, Dawid Wiśniewski, Agnieszka Ławrynowicz

Semi-structured text generation is a non-trivial problem. Although last years have brought lots of improvements in natural language generation, thanks to the development of neural models trained on large scale datasets, these approaches still struggle with producing structured, context- and commonsense-aware texts. Moreover, it is not clear how to evaluate the quality of generated texts. To address these problems, we introduce RecipeNLG - a novel dataset of cooking recipes. We discuss the data collection process and the relation between the semi-structured texts and cooking recipes. We use the dataset to approach the problem of generating recipes. Finally, we make use of multiple metrics to evaluate the generated recipes.

Paper PDF Code

Code

Glorf/recipenlg pytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Named Entity Recognition (NER)Recipe Generation Text Generation

Datasets

Introduced by this paper, per the archive.

RecipeNLG

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Recipe Generation	RecipeNLG	GPT2-small	BLEU	0.866	#1 of 1	Archive leaderboard	report
Recipe Generation	RecipeNLG	GPT2-small	GLEU	0.662	#1 of 1	Archive leaderboard	report
Recipe Generation	RecipeNLG	GPT2-small	Word Error Rate (WER)	0.751	#1 of 1	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Adam Attention Attention Dropout BPE Cosine Annealing Dense Connections Discriminative Fine-Tuning Dropout GPT-2 Layer Normalization Linear Layer Linear Warmup With Cosine Annealing Multi-Head Attention Residual Connection Softmax Weight Decay

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections