TASTEset -- Recipe Dataset and Food Entities Recognition Benchmark
This provides a benchmark for NLP in food computing, addressing a gap for researchers in this domain, though it is incremental as it builds on existing NER methods.
The authors tackled the lack of well-defined benchmarks in food computing by introducing TASTEset, a dataset of 700 recipes with over 13,000 entities for Named Entity Recognition, where the best model achieved an average F1 score of 0.95, ranging from 0.781 to 0.982 depending on entity type.
Food Computing is currently a fast-growing field of research. Natural language processing (NLP) is also increasingly essential in this field, especially for recognising food entities. However, there are still only a few well-defined tasks that serve as benchmarks for solutions in this area. We introduce a new dataset -- called \textit{TASTEset} -- to bridge this gap. In this dataset, Named Entity Recognition (NER) models are expected to find or infer various types of entities helpful in processing recipes, e.g.~food products, quantities and their units, names of cooking processes, physical quality of ingredients, their purpose, taste. The dataset consists of 700 recipes with more than 13,000 entities to extract. We provide a few state-of-the-art baselines of named entity recognition models, which show that our dataset poses a solid challenge to existing models. The best model achieved, on average, 0.95 $F_1$ score, depending on the entity type -- from 0.781 to 0.982. We share the dataset and the task to encourage progress on more in-depth and complex information extraction from recipes.