NATURAL LANGUAGE PROCESSING

CSE5NLP

2021

Credit points: 15

Subject outline

Natural Language Processing (NLP) is broadly concerned with the interactions between computers and natural (i.e., human) languages; more particularly, it is concerned with the question of how to program computers to process and analyse large amounts of natural language data. Following a review of the essential mathematical and linguistic concepts underlying natural language processing, you will develop skills in important natural language processing sub-tasks including accessing corpora, tokenisation, morphological analysis, word sense disambiguation, part-of speech tagging, and analysing sentence structure. You will then apply these skills in the context of applications such as text categorisation, text clustering, text recommendation, and information retrieval. Where appropriate, both lexical (i.e. dictionary-based) and machine learning approaches will be used.

SchoolEngineering and Mathematical Sciences

Credit points15

Subject Co-ordinatorAndrew Skabar

Available to Study Abroad/Exchange StudentsYes

Subject year levelYear Level 5 - Masters

Available as ElectiveNo

Learning ActivitiesN/A

Capstone subjectNo

Subject particulars

Subject rules

PrerequisitesCSE5AIF OR CSE2AIF

Co-requisitesN/A

Incompatible subjectsN/A

Equivalent subjectsN/A

Quota Management StrategyN/A

Quota-conditions or rulesN/A

Special conditionsN/A

Minimum credit point requirementN/A

Assumed knowledgeN/A

Readings

Foundations of Statistical Natural Language Processing

Resource TypeRecommended

Resource RequirementN/A

AuthorChristopher D. Manning and Hinrich Schutze.

Year1999

Edition/VolumeN/A

PublisherThe MIT Press

ISBNN/A

Chapter/article titleN/A

Chapter/issueN/A

URLN/A

Other descriptionN/A

Source locationN/A

Speech and Language Processing

Resource TypeRecommended

Resource RequirementN/A

AuthorDaniel Jurafsky and James H. Martin.

Year2014

Edition/VolumeN/A

PublisherPearson

ISBNN/A

Chapter/article titleN/A

Chapter/issueN/A

URLN/A

Other descriptionN/A

Source locationN/A

Natural Language Processing with Python

Resource TypeRecommended

Resource RequirementN/A

AuthorSteven Bird, Ewan Klein & Edward Loper

YearN/A

Edition/VolumeN/A

PublisherO'Reilly

ISBNN/A

Chapter/article titleN/A

Chapter/issueN/A

URLN/A

Other descriptionN/A

Source locationN/A

Career Ready

Career-focusedNo

Work-based learningNo

Self sourced or Uni sourcedN/A

Entire subject or partial subjectN/A

Total hours/days requiredN/A

Location of WBL activity (region)N/A

WBL addtional requirementsN/A

Graduate capabilities & intended learning outcomes

Graduate Capabilities

Intended Learning Outcomes

01. Apply natural language processing sub tasks, including tokenisation, morphological analysis, word sense disambiguation, part-of-speech tagging, and analysing sentence structure, to natural languages texts.
02. Describe and evaluate the methods and algorithms used to process different types of textual data.
03. Devise natural language processing(NLP)processing pipelines using existing NLP code libraries, textcorpora, and lexical resources such as WordNet.
04. Critically evaluate results of applying natural language processing methods to real-world tasks such as text categorisation, text clustering, text recommendation and information retrieval.

Subject options

Select to view your study options…

Start date between: and    Key dates

Melbourne (Bundoora), 2021, Summer, Day

Overview

Online enrolmentYes

Maximum enrolment sizeN/A

Subject Instance Co-ordinatorAndrew Skabar

Class requirements

Computer LaboratoryWeek: 46 - 0
One 2.00 h computer laboratory per week on weekdays during the day from week 46 to week 0 and delivered via face-to-face.

LectureWeek: 46 - 0
One 2.00 h lecture per week on weekdays during the day from week 46 to week 0 and delivered via face-to-face.

Assessments

Assessment elementCommentsCategoryContributionHurdle% ILO*
Assignment 1 (equivalent to 1500 words) Students write Python code to perform tokenisation, morphological analysis, word sense disambiguation and part-of-speech tagging.N/AN/AN/ANo20 SILO1, SILO2
Assignment 2 (equivalent to 2,000 words) Students apply their skills to tasks such as text categorisation, text clustering, text recommendation and information retrieval.N/AN/AN/ANo30 SILO2, SILO3, SILO4
Two-hour examination (equivalent to 2,000 words)N/AN/AN/ANo50 SILO1, SILO2, SILO3, SILO4