NPFL096 Computational Morphology

Instructor:	Jirka Hana
e-mail for homeworks etc:	Jirka.LastName@gmail.com (start the email's subject with NPFL096)
Time & Place:	Replaced by NPFL128 Language technologies in practice

 

1  Description and objectives of the course

Note: I am in the process of changing the topic of the class from focus on computational morphology to practical aspects of NLP in general. The exact mix of topics will be agreed in class.

This course will introduce you to the methods of processing morphology of natural languages. It covers both supervised and unsupervised methods of morphological analysis, morpheme segmentation, lexicon creation, etc. Most of the course consists of discussion of important papers in the field. You will replicate or extend a system from one of the papers.

 

2  Readings and discussion

In each class, we will discuss one or more papers (sometimes books or dissertations). It is expected that everybody will have read the papers. For each paper, one or two people will be responsible for leading the discussion (in some cases it will be me).

3  Project

There is one programming [Project] due on July 31 (talk to me if you cannot meet the deadline)

• Put everything into a single zip and put it somewhere on the web.
• Send me the zip's url in an email with subject "NPFL096 . "

Note: There are no home work assignments this year, instead invest some extra energy into the project. You were, however, supposed to send me a pseudo code of an inflectional morphological analyzer during the semester..

4  Active class participation

"Active participation" refers to your comments and questions during class, your answers to my questions, etc. I do not keep track of whether your answers, etc. are correct, but simply whether or not you participate. It is important that you read the assigned papers (especially if you are leading the discusssion).

5  Grading

6  Schedule

Note: I am in the process of changing the topic of the class from focus on computational morphology to practical aspects of NLP in general.

Date		Topic	Related/Other papers
27 Feb		Introduction; Morphology [slides] FS Technology; Morphological Analysis; Two-level morphology; Corpora, Tagsets, Annotation [slides]
6 Mar		A. Feldman & J. Hana (2010). A resource-light approach to morpho-syntactic tagging (Chapter 6, 7) [slides]
20 Mar		J. Goldsmith (2001). Unsupervised Learning of the Morphology of a Natural Language.
27 Mar		P. Schone & D. Jurafsky (2001): Knowledge-free induction of inflectional morphologies	P. J. Schone (2001): Toward knowledge-free induction of machine-readable dictionaries.
3 Apr		D. Yarowsky & R. Wicentowski (2000): Minimally Supervised Morphological Analysis by Multimodal Alignment.	R. Wicentowski (2004): Multilingual noise-robust supervised morphological analysis using the WordFrame model.
10 Apr		S.Cucerzan & D. Yarowsky (2002): Bootstrapping a Multilingual Part-of-speech Tagger in One Person-day _ (2003): Minimally Supervised Induction of Grammatical Gender
17 Apr		M. G. Snover & M. R. Brent (2001): A Bayesian model for morpheme and paradigm identification.	Morfessor: M. Creutz and K. Lagus (2007): Unsupervised models for morpheme segmentation and morphology learning. Helping Morfessor/Paramor (Kohonen et al 2010, Tepper and Xia 2008, Klíč and Hana)
24 Apr		Sentiment Analysis
15 May		Named Entity Recognition - Overview
22 May		Named Entity Recognition - Cucerzan (2007). Large-Scale Named Entity Disambiguation Based on Wikipedia Data

Links:

• 2013-esslli-2-res.pdf
• hana-feldman-2012-compass.pdf
• ACL Special Interest Group on Computational Morphology and Phonology.
• M. G. Snover & M. R. Brent (2001): A Bayesian model for morpheme and paradigm identification.
• Morfessor: M. Creutz and K. Lagus (2007): Unsupervised models for morpheme segmentation and morphology learning.
• Creutz, M (2006): Induction of the Morphology of Natural Language (thesis)
• C. Monson et al (2007). ParaMor: Minimally Supervised Induction of Paradigm Structure and Morphological Analysis.