F20AA Applied Text Analytics

Dr Neamat El Gayar

Course co-ordinator(s): Dr Neamat El Gayar (Dubai).

Aims:

This course aims to provide the students with knowledge and skills in applied text analytics focusing on Machine Learning and Natural Language Processing tools.

In particular the course:

- Presents the area of text analytics and provides fundamental tools to extract, represent and analyse information from text sources using machine learning models

- Provides a fundamental understanding of concepts and tools to build effective language aware systems and applications

- Presents basic understanding of deep learning models for Natural Language Processing applications and related research

- Discusses current research advances, business cases and future direction of the field

 

Detailed Information

Course Description: Link to Official Course Descriptor.

Pre-requisites: none.

Location: Dubai.

Semester: 2.

Syllabus:

Following topics will be covered with varying levels of depth:

- Overview on ML models, techniques and use cases & ML project design.

- Language model & text processing principles

- Text classification & visualization

- Text Clustering & topic modelling

- Context-aware text analysis & n-gram model

- Chatbots

- Scaling text analytics

- A deep learning approach to NLP:

o Sequence models (ex: RNN, BRNN, LSTM ) & transfer learning

o Applications in Named Entity Recognition, learning word-embeddings, machine translation, sentiment classification

- Research Directions and Business Cases

Learning Outcomes: Subject Mastery

- Demonstrate understanding of the text analytics process and relevant applications

- Work with text analytic tools to uncover information from text

- Understand challenges related to implementation and scalability

- Understand Deep learning approach to NLP problems and some available tools for implementation

- Demonstrate understanding of some recent advances in the field of NLP & text analytics.

Learning Outcomes: Personal Abilities

-Problem analysis and critical review

-Report writing and presentation skills

- Working in groups

-Use a range of software for ML, text analytics and NLP

 

Assessment Methods: Due to covid, assessment methods for Academic Year 2021/22 may vary from those noted on the official course descriptor. Please see:
- Maths (F1) Course Weightings 2021/22
- Computer Science (F2) Course Weightings 2021/22
- AMS (F7) Course Weightings 2021/22

SCQF Level: 10.

Credits: 15.