Brief Course Description
1. Course Title:
Natural Language Processing
2. Language of Instruction:
Tiếng Việt
3. Course Code:
M01369
4. Credits:
3
5. Course Objectives:
Equip students with basic knowledge of computational linguistics and specialized knowledge of natural language processing processes. It also provides students with libraries that support natural language processing.
6. Brief Description of Course Content:
Providing basic knowledge of natural language processing including: data collection, data cleaning, extracting features, building processing models, Students will be provided with the knowledge of libraries necessary to collect and build datasets from Internet sources such as news sites, etc. Wikipedia, social networks such as Twitter, Facebook, Youtube, e-commerce sites such as Shopee, Tiki. In the steps of cleaning and extracting data, in addition to the general steps, students are also introduced to the steps that are applied specifically to Vietnamese data. Regarding the exam processing model, students will be provided with basic knowledge about Machine Learning and Deep Learning to be able to solve basic problems such as classification, clustering, text summarization, and machine translation. Students will practice using the Python language on the Google Colab virtual machine in the course. At the end of the course, students will be able to collect and build English or Vietnamese datasets for natural language processing problems and know how to develop Machine Learning and Deep Learning models to solve these problems.