Gorjan Popovski
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Gorjan Popovski has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Tome Eftimov
Jozef Stefan Institute
7 shared publications - Barbara Koroušić Seljak
Jozef Stefan Institute
6 shared publications Tome Eftimov
6 shared publicationsBarbara Koroušić Seljak
3 shared publications- Dragi Kocev
Jožef Stefan Institute, Ljubljana, Slovenia
3 shared publications Barbara Korousic Seljak
Computer Systems Department, Jozef Stefan Institute, 1000 Ljubljana, Slovenia
2 shared publications
Latest Publications
- Open Access
- 25 March 2022
- Published by Elsevier in Trends in Food Science & Technology
- Vol. 123, 310-321
Workflow for building interoperable food and nutrition security (FNS) data platforms
- 25 March 2022
- Published by Elsevier in Trends in Food Science & Technology
- Vol. 123, 310-321
Open AccessWorkflow for building interoperable food and nutrition security (FNS) data platforms
- Open Access
- 9 August 2021
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 23 (8) , e28229
A Fine-Tuned Bidirectional Encoder Representations From Transformers Model for Food Named-Entity Recognition: Algorithm Development and Validation
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.
- 9 August 2021
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 23 (8) , e28229
Open AccessA Fine-Tuned Bidirectional Encoder Representations From Transformers Model for Food Named-Entity Recognition: Algorithm Development and Validation
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.
- Open Access
- 1 July 2021
- Published by Elsevier in Big Data Research
- Vol. 25
A Framework for Evaluating Personalized Ranking Systems by Fusing Different Evaluation Measures
- 1 July 2021
- Published by Elsevier in Big Data Research
- Vol. 25
Open AccessA Framework for Evaluating Personalized Ranking Systems by Fusing Different Evaluation Measures
- 30 March 2021
- Published by Springer Nature
- p. 468-485
Food Data Normalization Using Lexical and Semantic Similarities Heuristics
- 30 March 2021
- Published by Springer Nature
- p. 468-485
Food Data Normalization Using Lexical and Semantic Similarities Heuristics
- Open Access
- 25 February 2021
- Published by JMIR Publications Inc. in JMIR Preprints
A Fine-Tuned Bidirectional Encoder Representations From Transformers Model for Food Named-Entity Recognition: Algorithm Development and Validation (Preprint)
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.
- 25 February 2021
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessA Fine-Tuned Bidirectional Encoder Representations From Transformers Model for Food Named-Entity Recognition: Algorithm Development and Validation (Preprint)
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.
- 1 January 2021
- Published by Elsevier in Trends in Food Science & Technology
- Vol. 107, 183-194
DietHub: Dietary habits analysis through understanding the content of recipes
- 1 January 2021
- Published by Elsevier in Trends in Food Science & Technology
- Vol. 107, 183-194
DietHub: Dietary habits analysis through understanding the content of recipes
- 1 October 2020
- Published by Elsevier in Trends in Food Science & Technology
- Vol. 104, 268-272
COVID-19 pandemic changes the food consumption patterns
- 1 October 2020
- Published by Elsevier in Trends in Food Science & Technology
- Vol. 104, 268-272
COVID-19 pandemic changes the food consumption patterns
- 1 April 2020
- Published by Elsevier in Food and Chemical Toxicology
- Vol. 138, 111169
FoodEx2vec: New foods’ representation for advanced food data analysis
- 1 April 2020
- Published by Elsevier in Food and Chemical Toxicology
- Vol. 138, 111169
FoodEx2vec: New foods’ representation for advanced food data analysis
- Open Access
- 12 February 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 31586-31594
A Survey of Named-Entity Recognition Methods for Food Information Extraction
As great amounts of food-related information is presented in the form of heterogeneous textual data, computer-based methods are useful to automatically extract such information. One way to do this is to utilize Named-Entity Recognition (NER) methods that are broadly used in computer science for information extraction. Despite the existence of numerous and well-versed NER methods in the biomedical domain, the domain of food science still remains scarcely resourced. In this paper, we provide an overview and a comparison of named-entity recognition methods in the food domain, which can be used for automated extraction of food information from text. Four methods are discussed: FoodIE, NCBO (SNOMED CT), NCBO (OntoFood), and NCBO (FoodON). We compare them using a benchmark data set that consists of 1000 manually annotated recipes initially obtained from Allrecipes, which is the largest social network focused on food. After analysing the results from the evaluation, it is evident that FoodIE obtains very promising results compared to the other food named-entity recognition methods taken into consideration.
- 12 February 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 31586-31594
Open AccessA Survey of Named-Entity Recognition Methods for Food Information Extraction
As great amounts of food-related information is presented in the form of heterogeneous textual data, computer-based methods are useful to automatically extract such information. One way to do this is to utilize Named-Entity Recognition (NER) methods that are broadly used in computer science for information extraction. Despite the existence of numerous and well-versed NER methods in the biomedical domain, the domain of food science still remains scarcely resourced. In this paper, we provide an overview and a comparison of named-entity recognition methods in the food domain, which can be used for automated extraction of food information from text. Four methods are discussed: FoodIE, NCBO (SNOMED CT), NCBO (OntoFood), and NCBO (FoodON). We compare them using a benchmark data set that consists of 1000 manually annotated recipes initially obtained from Allrecipes, which is the largest social network focused on food. After analysing the results from the evaluation, it is evident that FoodIE obtains very promising results compared to the other food named-entity recognition methods taken into consideration.
- 1 January 2020
- Published by Springer Nature
- p. 413-426
FoodOntoMapV2: Food Concepts Normalization Across Food Ontologies
- 1 January 2020
- Published by Springer Nature
- p. 413-426
FoodOntoMapV2: Food Concepts Normalization Across Food Ontologies