Uppgifter om studieperioden
Visa undervisning och tenter
LDA-T3103 Datamodeller för semantik, 5 sp 
Kod LDA-T3103  Giltighet 01.01.2017 -
Namn Datamodeller för semantik  Förkortning Datamodeller fö 
Omfattning5 sp   
UndervisningsformFördjupade studier
Klass/KategoriStudieperiod   
  BedömningAllmän skala 
  nej
    Kan genomföras flera gångernej
Ansvarig enhet Magisterprogrammet i språklig diversitet och digitala metoder 

Lärare
Namn
Mathias Creutz 

Beskrivning
Målgrupp 

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 obligatory course for students of the study track in language technology, and elective for the students of LDA-TA500 and LDA-TB500.

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

 

 


 

 

 

 

 




 

 

 

 
Timing 

Students are advised to take this course in year 1 (semester 2) or year 2 (semester 3). The course is offered once every year either during the spring term in period IV or during the autumn term in period I or II

 
Kunskapsmål 

After successfully completing the course, you will be able to

  • explain common computational models of meaning representation
  • describe the main principles of symbolic methods in connection with logic and compositional semantics
  • describe the main principles of distributional semantics and representation learning in connection with vector space models
  • discuss issues of non-compositionality and idiomatic expressions
  • explain common methods for automatic word sense disambiguation, semantic role labeling, sentiment analysis and distributional representation learning.
 
Studieavsnittets form 
  • The course consists of lectures, lab sessions, tutorials and seminars.
  • There may also be a final exam.
  • Some sessions require student attendance.
 
Tidigare studier eller kunskaper 
  • Semantics and pragmatics or equivalent (BA level)
  • Programming for linguists or equivalent (BA level)
  • Mathematics for linguists or equivalent (BA level)
  • Machine learning for linguists or equivalent (BA level)
 
Rekommenderade valfria studier 
  • Linguistics in the digital age  (MA level)
  • Computational Morphology (MA level)
  • Computational Syntax (MA level)
 
Innehåll 

The meaning of words and phrases can be modeled computationally from rather different perspectives. This course provides an overview of the field covering topics, such as:

  • Meaning representations
  • Symbolic, subsymbolic and analogical representations
  • Lexical semantics, word senses, lexico-semantic relations (WordNet)
  • Compositional semantics, semantics and logic, semantic roles
  • Distributional semantics, vector-space models
  • Non-compositionality, multiword/idiomatic expressions (rhetorical figures, metaphors, sentiment).

There is also hands-on experience with some relevant algorithms, for instance:

  • Word-sense disambiguation
  • Semantic role labeling
  • Sentiment analysis
  • Representation learning
  • Word association and multiword expressions
 
Studiematerial och litteratur 
  • Jurafsky, Daniel; Martin, James H.: Speech and language processing : an introduction to natural language processing, computational linguistics and speech recognition, Prentice Hall cop. 2009. 2nd ed (especially for symbolic representations and methods)
  • Web material and material distributed on the course
 
Aktiviteter och undervisningsmetoder som stöder lärandet 
  • There are lectures, lab sessions and interactive seminars.
  • The students work both individually and by exchanging ideas in larger groups.
  • Exercises, instructions and additional course material are published on a web-based learning platform (Moodle).
 
Bedömningsmetoder och kriterier 

Grading follows the standard scale 0 – 5.

The following aspects are taken into account in grading

  • Performance in the exercises
  • Performance in the seminar work
  • Performance in the final exam
  • Active participation during sessions.
 


Pågående och framtida undervisning
Funktioner Namn Typ sp Lärare Tid
Anmäl dig Computational Semantics  Kurs  Mathias Creutz 
28.10.19 -09.12.19 må 10.15-11.45
30.10.19 -11.12.19 ons 12.15-13.45

Framtida tenter
Inga tenter i WebOodi