Natural Language Processing (Classroom and Asynchronous e-learning)
About This Course
This course provides a comprehensive introduction to Natural Language Processing (NLP), guiding learners from foundational principles to cutting-edge technologies. It emphasizes hands-on experience, as learners apply advanced NLP methods—including attention-based deep learning models—to practical projects such as machine translation and text summarization using real-world datasets. With the rapid emergence of Artificial Intelligence-powered generative tools such as ChatGPT, NLP expertise is increasingly critical in research, development, and enterprise sectors. Equipped with essential skills in machine learning and deep learning, learners will be effectively prepared for careers in data science and artificial intelligence.
As this micro-credential course is only offered in the FlexiMasters in Signal Processing and Machine Learning programme, learners are required to enrol into the programme and complete all required courses within this programme.
What You'll Learn
• Identify the appropriateness of Natural Language Processing (NLP) preprocessing techniques in different contexts.
• Explain the mathematical derivations of traditional NLP methods such as term weighting schemes, feature extraction techniques, and topic modelling.
• Execute simple NLP tasks such as classification and clustering on small-scale problems and evaluate the algorithm performance.
• Implement NLP algorithms in Python programming language.
• Distinguish between the theoretical concepts of traditional and deep neural network-based NLP techniques.
• Formulate the construction of word embeddings and model training using deep neural network-based architecture such as Recurrent Neural Network (RNN), Seq2Seq, Attention mechanism, and transformers.
• Describe the working principles of pre-trained language models.
• Design NLP-based project as a team to solve a real-life application by employing any techniques learnt along with fine-tuning the model.
Entry Requirements
No pre-requisites are needed to enroll in the individual courses; however, learners without qualifications or working experience in relevant engineering or the related fields may find the course contents challenging. Note: Shortlisting will be conducted.