Computational Morphology

Introductory course in Language and Computation, taught at ESSLLI 2013

25th European Summer School in Logic, Language and Information, Heinrich Heine University in Düsseldorf, Germany, August 5-16, 2013

This material is based upon work supported by the National Science Foundation under Grant No. 0916280

Below, you will find an overview of the course topics as well as copies of the slides for download. We also provided a list of relevant texts and tools.

Course reader: [pdf]

Additional readings:

Jirka Hana and Anna Feldman. 2012. Resource-light approaches to computational morphology. Part I: Monolingual Approaches . In Language and Linguistics Compass Journal (Computational Linguistics Section). Vol.6, Issue 10, pp. 622-634, Blackwell.[preprint]

Course structure:

    Day 1: Introduction; Basics of morphology.    Slides [pdf]     Exercise 1 [pdf]     Exercise 2 [pdf]
    Day 2: Classical Approaches to Computational Morphological Analysis;            Slides [pdf]
    Day 3: Classical tagging techniques.     Slides [pdf]
    Day 4: Unsupervised and Resource-light Approaches to Computational Morphology; Tagset Design . Slides 1 [pdf] Slides 2 [pdf]
    Day 5:    Our resource-light approach to morphology. Practical aspects.     Slides [pdf]

Texts

Christopher D. Manning, Hinrich Schuetze (1999). Foundations of Statistical Natural Language Processing [Amazon]
Daniel Jurafsky and James H. Martin (2009). Speech and Language Processing. Prentice Hall; 2 edition. [Amazon]
Anna Feldman and Jirka Hana (2010). A resource-light approach to morpho-syntactic tagging. Rodopi, Amsterdam/New York, NY, 199pp. [Amazon] [Amazon UK]

Various tools

SFST -- Stuttgart Finite State Transducer Tools SFST is a toolbox for the implementation of morphological analysers and other tools which are based on finite state transducer technology.
OpenFst Library A library for constructing, combining, optimizing, and searching weighted finite-state transducers (FSTs).
Foma: a finite-state compiler and library
FSA6.2xx: : FSA Utilities toolbox: a collection of utilities to manipulate regular expressions, finite-state automata and finite-state transducers. (SICStus Prolog, SWI-Prolog or YAP)
HFST : Helsinki Finite State Transducer Technology
TnT tagger -- a very efficient statistical part-of-speech tagger
Jitar HMM part of speech tagger : An open source java implementation of a simple Trigram HMM part-of-speech tagger, based on TnT