COMP SCI 7417 - Applied Natural Language Processing

North Terrace Campus - Semester 1 - 2022

This course examines machine learning techniques that obtain leading results on the problem of natural language processing (NLP). NLP is a critical step towards effective communication between people and machines. You will learn how to represent words and text, the use of deep recurrent models for text prediction, and issues that separate NLP from other application domains. This will be reinforced by applying deep learning tools to NLP through examples and practical projects.

  • General Course Information
    Course Details
    Course Code COMP SCI 7417
    Course Applied Natural Language Processing
    Coordinating Unit Computer Science
    Term Semester 1
    Level Postgraduate Coursework
    Location/s North Terrace Campus
    Units 3
    Contact Up to 2 hours per week
    Available for Study Abroad and Exchange
    Assumed Knowledge COMP SCI 7317
    Course Description This course examines machine learning techniques that obtain leading results on the problem of natural language processing (NLP). NLP is a critical step towards effective communication between people and machines. You will learn how to represent words and text, the use of deep recurrent models for text prediction, and issues that separate NLP from other application domains. This will be reinforced by applying deep learning tools to NLP through examples and practical projects.
    Course Staff

    Course Coordinator: Dr Lingqiao Liu

    Course Timetable

    The full timetable of all activities for this course can be accessed from Course Planner.

  • Learning Outcomes
    Course Learning Outcomes
    On successful completion of this course, students will be able to:

    1 Understand the basic concepts and basic algorithms of Natural language processing.
    2 Ability to use existing natural language processing tools to conduct basic natural language processing, such as text normalization, named entity extraction, or syntactic parsing.
    3 Ability to use machine learning tools to build solutions for natural language processing problems.
    4 Ability to decompose a real-world problem into subproblems in natural language processing and identify potential solutions.




    University Graduate Attributes

    This course will provide students with an opportunity to develop the Graduate Attribute(s) specified below:

    University Graduate Attribute Course Learning Outcome(s)

    Attribute 1: Deep discipline knowledge and intellectual breadth

    Graduates have comprehensive knowledge and understanding of their subject area, the ability to engage with different traditions of thought, and the ability to apply their knowledge in practice including in multi-disciplinary or multi-professional contexts.

    1,2,3,4

    Attribute 2: Creative and critical thinking, and problem solving

    Graduates are effective problems-solvers, able to apply critical, creative and evidence-based thinking to conceive innovative responses to future challenges.

    1,2,3,4

    Attribute 3: Teamwork and communication skills

    Graduates convey ideas and information effectively to a range of audiences for a variety of purposes and contribute in a positive and collaborative manner to achieving common goals.

    3,4

    Attribute 4: Professionalism and leadership readiness

    Graduates engage in professional behaviour and have the potential to be entrepreneurial and take leadership roles in their chosen occupations or careers and communities.

    4

    Attribute 5: Intercultural and ethical competency

    Graduates are responsible and effective global citizens whose personal values and practices are consistent with their roles as responsible members of society.

    4

    Attribute 7: Digital capabilities

    Graduates are well prepared for living, learning and working in a digital society.

    2,3

    Attribute 8: Self-awareness and emotional intelligence

    Graduates are self-aware and reflective; they are flexible and resilient and have the capacity to accept and give constructive feedback; they act with integrity and take responsibility for their actions.

    1,2,3,4
  • Learning Resources
    Required Resources
    All required resources for this course will be provided online via the MyUni platform.
    Recommended Resources
    Recommended books:

    1. Speech and Natural Language Processing by Dan Jurafsky and James H. Martin
    2. Applied Natural Language Processing with Python by Beysolow II, Taweh

    Some parts of the lecture slides are based on book 1. 
    Online Learning
    Our course forum is accessible via the Canvas.

    Excellent external courses available online:
    1. CS224n: Natural Language Processing with Deep Learning
    http://web.stanford.edu/class/cs224n/
    2. Natural Language Processing 
    https://www.youtube.com/watch?v=3Dt_yh1mf_U&list=PLQiyVNMpDLKnZYBTUOlSI9mi9wAErFtFm
  • Learning & Teaching Activities
    Learning & Teaching Modes
    The course will be primarily delivered through three activities:

    - Lectures
    - Workshops
    - Assignments

    Lectures will introduce and motivate the basic concepts of each topic. Significant discussions and two-way communication are also expected during lectures to enrich the learning experience. The workshops will discuss how to apply the knowledge from lectures to practical problems. The assignments will reinforce concepts by their application to problem solving. This will be done via programming work. All material covered in the lectures and assignments are assessable.
    Workload

    The information below is provided as a guide to assist students in engaging appropriately with the course requirements.

    Students are expected to spend 9-10 hours per week on this course.
    There will be 1-2 hours contact time for learning and teaching activities and students will be working individually and in groups 8-9 hours to carry out the required learning and teaching activities for acquiring the expected knowledge, understanding and skills in this course.
    Learning Activities Summary
    Students are encouraged to attend lectures as material presented in lectures often includes more than is on the slides. Students are also encouraged to ask questions during the lectures. Slides will be available via the subject web page.

    This is a 3-unit course. Students are expected to spend about 8 hours per week on the course. This includes a 2-hour lecture, 2-hour self study and up to 4 hours per week on completing assignments.

    Assigmment work will be subjected to deadlines. Students are expected to manage their time effectively to allow timely submission, especially with consideration to workload of other courses.

    Specific Course Requirements
    Knowing some basic statistics, probability, linear algebra and optimisation would be helpful, but not essential. They will be covered when needed.

    Ability to program in Python is required.
  • Assessment

    The University's policy on Assessment for Coursework Programs is based on the following four principles:

    1. Assessment must encourage and reinforce learning.
    2. Assessment must enable robust and fair judgements about student performance.
    3. Assessment practices must be fair and equitable to students and give them the opportunity to demonstrate what they have learned.
    4. Assessment must maintain academic standards.

    Assessment Summary
    Three assignments involving coding practice for solving NLP problems. Three mini-quizes focused on the theoretical part of the subject. Each mini-quiz consists of less than 4 questions and will take less than 1 hour to complete.

    Assessment Detail
    Assignment 1: Building a sentiment analysis system with Naïve Bayes

    Due: Week 6 (tentative)
    Percentage of grade: 25%
    Type: Open-book
    Assessment Documents: Code and Report
    Mini-quiz 1: Text processing, TF-IDF and Naïve Bayes

    Due: Week 5 (tentative)
    Percentage of grade: 5%
    Type: Quiz
    -----------------------------------

    Assignment 2: Building a text matching algorithm for question retrieval

    Due: Week 9 (tentative)
    Percentage of grade: 25%
    Type: Open-book
    Assessment Documents: Code and Report
    Mini-quiz 2: Part-of-Speech Tagging and Parsing

    Due: Week 10 (tentative)
    Percentage of grade: 5%
    Type: Quiz
    -------------------------------------------

    Assignment 3: Building an Aspect-based Sentiment Analysis System

    Due: Week 13 (tentative)
    Percentage of grade: 30%
    Type: Open-book
    Assessment Documents: Code and Report


    Mini-quiz 3: Apply NLP for Solving Practical Problems

    Due: Week 13 (tentative)
    Percentage of grade: 10%
    Type: Quiz

    Submission
    Submission details for all activities are available in MyUni but the majority of your submissions will be online and may be subjected to originality testing through Turnitin or other mechanisms. You will receive clear and timely notice of all submission details in advance of the submission date.
    Course Grading

    Grades for your performance in this course will be awarded in accordance with the following scheme:

    M10 (Coursework Mark Scheme)
    Grade Mark Description
    FNS   Fail No Submission
    F 1-49 Fail
    P 50-64 Pass
    C 65-74 Credit
    D 75-84 Distinction
    HD 85-100 High Distinction
    CN   Continuing
    NFE   No Formal Examination
    RP   Result Pending

    Further details of the grades/results can be obtained from Examinations.

    Grade Descriptors are available which provide a general guide to the standard of work that is expected at each grade level. More information at Assessment for Coursework Programs.

    Final results for this course will be made available through Access Adelaide.

  • Student Feedback

    The University places a high priority on approaches to learning and teaching that enhance the student experience. Feedback is sought from students in a variety of ways including on-going engagement with staff, the use of online discussion boards and the use of Student Experience of Learning and Teaching (SELT) surveys as well as GOS surveys and Program reviews.

    SELTs are an important source of information to inform individual teaching practice, decisions about teaching duties, and course and program curriculum design. They enable the University to assess how effectively its learning environments and teaching practices facilitate student engagement and learning outcomes. Under the current SELT Policy (http://www.adelaide.edu.au/policies/101/) course SELTs are mandated and must be conducted at the conclusion of each term/semester/trimester for every course offering. Feedback on issues raised through course SELT surveys is made available to enrolled students through various resources (e.g. MyUni). In addition aggregated course SELT data is available.

  • Student Support
  • Policies & Guidelines
  • Fraud Awareness

    Students are reminded that in order to maintain the academic integrity of all programs and courses, the university has a zero-tolerance approach to students offering money or significant value goods or services to any staff member who is involved in their teaching or assessment. Students offering lecturers or tutors or professional staff anything more than a small token of appreciation is totally unacceptable, in any circumstances. Staff members are obliged to report all such incidents to their supervisor/manager, who will refer them for action under the university's student’s disciplinary procedures.

The University of Adelaide is committed to regular reviews of the courses and programs it offers to students. The University of Adelaide therefore reserves the right to discontinue or vary programs and courses without notice. Please read the important information contained in the disclaimer.