GRADUATION THESIS BACHELOR OF ENGINEERING IN INFORMATION TECHNOLOGY (HIGH-QUALITY PROGRAM)

Abstract

Plagiarism has always been a serious problem in academia, but with the advancement of technology, plagiarism is becoming more sophisticated and complex than ever. To process an ever-increasing amount of data, the applied of deep learning machine models for data processing is a necessity in the development of a plagiarism detection system. With the success of neural language models such as BERT has been proven in various NLP tasks by many organizations and communities in the past few years. In this thesis, we will review and applied Vietnamese BERT like (viBERT and PhoBERT) model for text encoding process. The result after encoding will be set of vectors that represent input text data include the context of each sentence. Also, in this thesis we will briefly introduce and testing with some of the services provided by Amazon Web Services to create a sample plagiarism detection system that using microservice architecture. With microservice, this system can run independently make it easier for deploy, maintenance, or scale up the system in the future.