Akademik Veri Yönetim Sistemi
2019 4th International Conference on Computer Science and Engineering (UBMK), Samsun, Turkey, Türkiye, 11 - 15 Eylül 2019
To be able to use supervised machine learning methods in natural language processing, there is a need of labeled data in large quantities. In some cases, especially when there are multiple tasks conducted on the same data, the annotation process may become exhausting and time consuming for both the annotatore and interpreters. Thus, an effective annotation tool becomes crucial in order to both increase the annotation quality and reduce the annotation time. In this paper, a semi-automatic annotation tool, which aims to decrease the manual work and user faults, is proposed. The interface of the tool is designed in a user-friendly manner in order to ease the process. The characteristics and input/output formats of the tool is explained in detail within the paper. The effects on the speed and accuracy of the users are analyzed as well as automatic labeling accuracy with conducted performance tests. It is noted that a deep-learning model trained with a small dataset can decrease the manual entity annotation workload up to 78,43%.