A Fine-Tuned Bidirectional Encoder Representations From Transformers Model for Food Named-Entity Recognition: Algorithm Development and Validation

Abstract

Background Recently, food science has been garnering a lot of attention. There are many open research questions on food interactions, as one of the main environmental factors, with other health-related entities such as diseases, treatments, and drugs. In the last 2 decades, a large amount of work has been done in natural language processing and machine learning to enable biomedical information extraction. However, machine learning in food science domains remains inadequately resourced, which brings to attention the problem of developing methods for food information extraction. There are only few food semantic resources and few rule-based methods for food information extraction, which often depend on some external resources. However, an annotated corpus with food entities along with their normalization was published in 2019 by using several food semantic resources. Objective In this study, we investigated how the recently published bidirectional encoder representations from transformers (BERT) model, which provides state-of-the-art results in information extraction, can be fine-tuned for food information extraction. Methods We introduce FoodNER, which is a collection of corpus-based food named-entity recognition methods. It consists of 15 different models obtained by fine-tuning 3 pretrained BERT models on 5 groups of semantic resources: food versus nonfood entity, 2 subsets of Hansard food semantic tags, FoodOn semantic tags, and Systematized Nomenclature of Medicine Clinical Terms food semantic tags. Results All BERT models provided very promising results with 93.30% to 94.31% macro F1 scores in the task of distinguishing food versus nonfood entity, which represents the new state-of-the-art technology in food information extraction. Considering the tasks where semantic tags are predicted, all BERT models obtained very promising results once again, with their macro F1 scores ranging from 73.39% to 78.96%. Conclusions FoodNER can be used to extract and annotate food entities in 5 different tasks: food versus nonfood entities and distinguishing food entities on the level of food groups by using the closest Hansard semantic tags, the parent Hansard semantic tags, the FoodOn semantic tags, or the Systematized Nomenclature of Medicine Clinical Terms semantic tags.

CafeteriaFCD Corpus: Food Consumption Data Annotated with Regard to Different Food Semantic Resources

“…Providing an annotated corpus with regard to different semantic resources allows us to further train information extraction methods using the state of the art in NLP. These resources were further utilized for training NER methods and their utility has already been published in [ 23 ].…”

Revisiting Named Entity Recognition in Food Computing: Enhancing Performance and Robustness

“…In the specific domain of food computing, a series of research works have applied state-of-the-art models on unique food-centric corpora. For instance, explorations leveraging the FoodBase dataset (Popovski et al, 2019) have utilized models like Bidirectional LSTM (BiLSTM) (Cenikj et al, 2020), and fine-tuning BERT and its variants (Perera et al, 2022;Stojanov et al, 2021;Cenikj et al, 2021). Further advances in the field have been made following the presentation of the TASTEset dataset (Wróblewska et al, 2022), introducing a novel benchmark through the strategic fine-tuning of BERT integrated with a CRF layer.…”

SciFoodNER: Food Named Entity Recognition for Scientific Text

“…The second corpus-based NER method for the food domain, FoodNER [20], performs finetuning of BERT [21] and BioBERT [9] for the NER task using the annotations from the FoodBase corpus. Apart from identifying the mentions of food entities from the text, the FoodNER model is also capable of performing NEL, i.e.…”