A Systematic Literature Review on Custom NER with Evidence-Based Software Engineering
Sivas Cumhuriyet Üniversitesi Mühendislik Fakültesi Dergisi, cilt.1, sa.2, ss.75-81, 2023 (Hakemli Dergi)
- Yayın Türü: Makale / Derleme
- Cilt numarası: 1 Sayı: 2
- Basım Tarihi: 2023
- Dergi Adı: Sivas Cumhuriyet Üniversitesi Mühendislik Fakültesi Dergisi
- Sayfa Sayıları: ss.75-81
- Sivas Cumhuriyet Üniversitesi Adresli: Evet
Özet
As the significance of data continues to grows, so does the importance of data analysis methods. Various models are currently being applied, and new models are being proposed all the time. In the context of this study, we conducted a detailed review of Named-Entity Recognition, a data analysis model. We applied the Evidence-Based Software Engineering method, which has been used successfully for many years, as the analysis method. The study analyzed 38 articles selected from a collection of 114 different research articles identified by this method. A detailed presentation of the analyzed data is provided. The study aimed to identify the most effective among the methods using NER. The analysis indicates that BERT was the most successful method in NER studies. It has been found that the "News" domain contains the highest number of NER datasets. The study also provides detailed information on other methods and domains dentified. As an original and comprehensive guide, this study serves as an excellent resource for those interested in the field.