Data on the course
Show instruction and examinations
LDA-T3105 Models and Algorithms in NLP-Applications, 5 cr 
Code LDA-T3105  Validity 01.01.2017 -
Name Models and Algorithms in NLP-Applications  Abbreviation Models and Algo 
Scope5 cr   
TypeAdvanced studies
TypeCourse   
  GradingGeneral scale 
  no
    Can be taken more than onceno
Unit Master’s programme Linguistic Diversity in the Digital Age 

Teachers
Name
Jörg Tiedemann 

Description
Target group 

The course belongs to the MA Programme Linguistic Diversity in the Digital Age

  • study track: language technology
  • modules: Studies in Language Technology (LDA-T3100), Essentials in Language Technology (LDA-TA500), Comprehensive specialization in Language Technology (LDA-TB500)

This is an optional course.

The course is available to students from other study tracks and degree programmes.

 

 

 

 

 
Timing 

Students are advised to take this course in year 2 (semester 3). The course is offered every year during the autumn term in period I or II.

 
Learning outcomes 

After successfully completing the course, students will be able to

  • explain models and algorithms used in selected NLP applications
  • describe properties of local prediction models and structural prediction models and methods that can be used to train them
  • explain the differences between generative and discriminative models and between supervised and unsupervised learning
  • describe the main components of a selected NLP application, for example a machine translation system
  • train and evaluate a practical NLP model, for example a statistical or neural machine translation model
  • present experimental results in a sound and scientific manner.
 
Completion methods 
  • Contact teaching (lectures, tutorials, seminars)
  • Self studies and group work

Examination:

  • one or more of the following: flipped classroom activities, overview paper, written exam (part I)
  • project report and presentation with peer-review (part II)

 

 
Prerequisites 
  • Programming for linguists or equivalent (BA level)
  • Mathematics for linguists or equivalent (BA level)
  • Machine learning for linguists or equivalent (BA level)
 
Recommended optional studies 
  • Linguistics in the digital age
  • Computational syntax
  • Computational semantics
  • Computational morphology
 
Contents 

Part I: Models and algorithms used in common NLP applications with focus on a selected application, for example machine translation

  • common models and their components (with focus on the selected application)
  • algorithms for training, tuning and evaluating NLP applications (with focus on the selected application).

Part II: Practical project work

  • data collection
  • training and tuning models
  • evaluating and analysing.
 
Study materials and literature 

The literature depends on the selected application, for example Philipp Koehn: "Statistical Machine Translation" (Cambridge University Press) in case of machine translation.

Other recommended literature: Manning and Schütze: Foundations of Statistical Natural Language Processing (MIT Press).

Additional web material and literature distributed on the course.

 
Activities and teaching methods in support of learning 
  • Lectures and tutorials
  • Interactive sessions, for example flipped classroom activities
  • Problem-based collaborative project work
  • Seminars with peer-review
  • Activities documented in Moodle
 
Assessment practices and criteria 

Part I:

  • Classroom activities (presentations and discussions)
  • Written exam or term paper

Part II:

  • Individual and collaborative work
  • Project report
  • Seminar presentation and peer review.
 


Current and future instruction
No instruction in WebOodi

Future examinations
No examinations in WebOodi