Module Details

The information contained in this module specification was correct at the time of publication but may be subject to change, either during the session because of unforeseen circumstances, or following review of the module at the end of the session. Queries about the module should be directed to the member of staff with responsibility for the module.
Title Natural Language Processing and Understanding
Code CSCK507
Coordinator Dr F Grasso
Computer Science
Floriana@liverpool.ac.uk
Year CATS Level Semester CATS Value
Session 2019-20 Level 7 FHEQ Whole Session 15

Aims

1. To provide students with a deep and systematic understanding of the theoretical underpinning supporting the domain of natural language processing.

2. To provide students with a comprehensive understanding of the tools and techniques of natural language processing and understanding and the ability to deploy such tools and techniques.

3. To provide students with the ability to apply the principles, methods and tools of natural language processing and understanding to provide solutions to business problems.


Learning Outcomes

(M1) A deep and systematic understanding of the nature of Natural Language Processing (NLP) in the context of modern commercial settings.

(M2) A critical understanding of the theory underpinning the practical application of NLP.

(M3) A comprehensive and wide-ranging understanding of the tools and techniques employed in the domain of NLP and an ability to apply those tools.

(M4) A comprehensive understanding of the nature of Chat Bots in the context of NLP and an ability to create simple but effective Chat Bot applications

(S1) Communication skills in electronic as well as written form.

(S2) Self-direction and originality in tackling and solving problems.

(S3) An ability to act autonomously and professionally when planning and implementing solutions to computer science problems.

(S4) Experience of working in development teams, respecting others, co-operating, negotiating/persuading, awareness of interdependence with others.


Syllabus

 

Week 1: The NLP landscape
NLP with the context of Artificial Intelligence and Data Science. Applications of NLP. NLP in the workplace. Available tool kits and frameworks such as PyTorch and spaCy.

Week 2: Text and sentence representation
Word embedding, vector representations of text, Bag of Words, nGrams. Regular expressions and word tokenization

Week 3: Sentiment Analysis
Applications of sentiment analysis and opinion mining, tools and techniques.

Week 4: Named–entity recognition
Applications and tools for named-entity recognition, and relation extraction.

Week 5: Sequence to sequence models.
Sequence to sequence models (seq2seq) in machine translation, voice-enabled devices and online chatbots, seq2seq model generation using Recurrent Neural Networks.

Week 6: Conversational user interfaces
Application in the business context, tools and techniques.

Week 7: Chat Bots
Goal oriented chat bots, Chit-chat bots, deve loping chat bots using available tools and techniques.

Week 8: Ethical considerations
Case studies, privacy and identity concerns.


Teaching and Learning Strategies

The mode of delivery is by online learning, facilitated by a Virtual Learning Environment (VLE). This mode of study enables students to pursue modules via home study while continuing in employment. Module delivery involves the establishment of a virtual classroom in which a relatively small group of students (usually 10-25) work under the direction of a faculty member. Module delivery proceeds via a series of eight one-week online sessions, each of which comprises an online lecture, supported by other eLearning activities, posted electronically to a public folder in the virtual classroom. The eLearning activities will include lecture casts, live seminar sessions, self-assessment activities, reading materials and other multimedia resources. Communication within the virtual classroom is asynchronous, preserving the requirement that students are able to pursue the course in their own time, within the weekly time-frame of each seminar. An important element of the module provision is act ive learning through collaborative, cohort-based, learning using discussion fora where the students engage in assessed discussions facilitated by the faculty member responsible for the module. This in turn encourages both confidence and global citizenship (given the international nature of the online student body).


Teaching Schedule

  Lectures Seminars Tutorials Lab Practicals Fieldwork Placement Other TOTAL
Study Hours 24

        40

64
Timetable (if known)              
Private Study 86
TOTAL HOURS 150

Assessment

EXAM Duration Timing
(Semester)
% of
final
mark
Resit/resubmission
opportunity
Penalty for late
submission
Notes
             
CONTINUOUS Duration Timing
(Semester)
% of
final
mark
Resit/resubmission
opportunity
Penalty for late
submission
Notes
Group Presentation: Chat Bot group project resulting in a demonstrable system and group video report (10 minutes) describing and analysing the approach taken and the system developed.  12 hours    30       
Programming: Individual software solution to a natural language processing problem resulting in a demonstrable system and supporting analysis in the form of a brief report (500 words)  12 hours    30       
Discussion question 2: Actively participate in online discussion on a specific topic related to natural language processing and understanding, demonstrating an understanding of the key issues and show  1000-1500 words    20       
Discussion Question 1: Participate actively in an online discussion concerning the issue and challenges of natural language processing and understanding, demonstrating an understanding of the key issu  1000-1500 words    20       

Recommended Texts

Reading lists are managed at readinglists.liverpool.ac.uk. Click here to access the reading lists for this module.