Text Processing using Machine Learning

About This Course

We are in an era where AI and analytics are transforming industries and people�s life at an unprecedented pace. In the recently released report from Gartner, Top 10 Strategic Technology Trends for 2018, the top two trends are AI Foundation, and Intelligent Apps and Analytics.
AI Foundation focuses on creating systems that learn, adapt and potentially act autonomously, and leveraging AI to enhance decision making, reinvent business models and ecosystems, and remake the customer experience. The technologies and techniques in AI Foundation have grown substantially over the years, as the availability of massive amounts of data has fed machine learning, resulting in the flourishing of more advanced algorithms in the form of deep learning.

The second trend, Intelligent Apps and Analytics, clearly states AI�s huge impact in the next-generation data and analytics paradigm, Augmented Analytics. Machine learning is key in this new paradigm, automating data preparation, insight discovery and insight sharing for a broad range of end-users and citizen data scientists, while expert data scientists focusing on specialised problems and on embedding models into applications. The need to perform processing on natural language data is reflected in the illustrated paradigm, identifying three tasks in this area � natural language processing (NLP), natural language query (NLQ), natural language generation (NLG).

In the field of NLP, deep learning techniques has taken a dominant position over tradition statistical methods. Researchers have been reporting much higher performance metrics applying deep learning to solve problems like text classification, language modeling, speech recognition, caption generation, machine translation, document summarisation, question answering, etc.

This course, Text Processing Using Machine Learning, provides essential knowledge and skills required to perform deep learning based text processing in common tasks encountered in industries. A combination of lectures, case studies, and workshops will be used to cover the application of DL techniques such as word-embedding, Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), LSTMs, character-based language modelling, encoder-decoder models, reinforcement learning, etc.