Algorithms of Language Technology 2016

Description 

How does language technology work? How does a computer recognize parts- of-speech? How can we utilize synonyms for search? How does automatic translation work? The theme of this lecture are algorithms used in language technology applications. This includes machine learning methods, data structures for string storage and manipulation, and applications like question answering systems or machine translation. The accompanying exercises offer some hands-on experience with language processing software, and in-depth understanding of algorithms.

Organization

     

  • Lecture: Wed, 13:30 - 15:10, Room S2|02|C110, starting April 13, 2016
  • Practice class: Tue, 15:20 - 17:00, Room S1|05|23, starting April 19, 2016
  •  

The learning material is available from the Moodle eLearning platform.

The required passcode will be distributed during the lecture.

Course Content

 

  • Recap: Chomsky Hierarchy: Formal Languages and Automata 
  • Morphology with Finite State Transducers and Compact Patricia Tries 
  • N-gram models: Entropy, Perplexity, Maximum Likelihood, Back-off and Smoothing 
  • Sequence Tagging: 

    • Markov Models
    • HMMs
    • CRFs

  • Context-free Grammars, Push-down automaton and PCFGs
  • Parsing algorithms: 

    • Top-down 
    • Bottom-up 
    • Shift-Reduce

  • Machine Translation

    • Alignment 
    • Decoding
    • Phrase-based SMT

  • Topic Modelling
  • Distributional Semantics

    • similarity measures
    • large-scale implementation

  • Graph representations and Graph algorithms for NLP

    • Word Sense Induction
    • TextRank

Exam

The exam will be announced during the lecture.

Literature

  • Selected Chapters from Jurafsky, D. and Martin, J. H. (2009): Speech and Language Processing. An Introduction to Natural Language Processing, Computational Linguistics and Speech Recognition. Second Edition. Pearson: New Jersey
  • Selected Chapters from Manning, C. D. and Schütze, H. (1999): Foundations of Statistical Natural Language Processing. MIT Press: Cambridge, Massachusetts 
  • Selected Chapters from Carstensen, K.U., Ebert, Ch., Endriss, C., Jekat, S., Klabunde, R. and Langer, H. (Editors) (2004): Computerlinguistik und Sprachtechnologie. Eine Einführung. 2. Auflage. Spektrum: Heidelberg   
  • Literature for specialized topics will be given in-place.

 

Lecturers

A A A | Drucken Print | Impressum Impressum | Sitemap Sitemap | Suche Search | Kontakt Contact | Webseitenanalyse: Mehr Informationen
zum Seitenanfangzum Seitenanfang