Erweiterte Suche | Seiten im Überblick

Computational Morphology

Kursbeschreibung

Dozenten/-innen	Jan Snajder
Veranstaltungsart	Wahlweise Pro- oder Hauptseminar
Erster Termin	17.04.2013
Zeit und Ort	Mi, 16:15–17:45, INF 325 / SR 23 (SR)
Commitment-Frist	20.05.–13.07.2013

Teilnahmevoraussetzungen

• Einführung in die Sprachwissenschaft
• Einführung in die Computerlinguistik
• Formale Grundlagen der Computerlinguistik: Mathematische Grundlagen

Leistungsnachweis

• Aktive und regelmäßige Teilnahme
• Wöchentliches vorbereitendes Lesen der Papiere
• Proseminar: schriftliche Ausarbeitung des Referats
• Hauptseminar: schriftliche Ausarbeitung einer erweiterten Fassung des Referats bzw. praktische Implementation des Ansatzes inklusive Evaluation und Dokumentation (jeweils nach Absprache)

Unterrichtssprache: Englisch (Referat/Seminararbeit auf Deutsch oder Englisch)

Inhalt

Computational morphology studies the theories and methods for computational analysis and synthesis of word forms. Morphological analysis is a prerequisite for many natural language processing tasks, such as part-of-speech tagging, parsing, and other higher-level tasks. Morphological analysis also plays an important role in many information retrieval tasks, especially for morphologically complex languages such as the Finish language, many other European languages, most Slavic and Semitic languages, etc. In this seminar course we will read and discuss the relevant literature on computational morphology. We will begin with an overview of the field and outline the basic tasks (analysis, segmentation, clustering, stemming, and lemmatization), approaches, and challenges. We will then be looking at different aspects of computational morphology, ranging from the basic models (finite state-based models and alternatives) to morphology learning (supervised and unsupervised), evaluation methodologies, and applications (in information retrieval and other fields). We will consider inflectional, but also derivational morphology, which is also interesting from a lexical semantics point of view. We will put an emphasis on the task of unsupervised morphology learning, relevant in particular for the many under resourced-languages, and discuss the recent developments in this line of research. This seminar course is appropriate for advanced undergraduate and graduate students.

Kursübersicht

Seminarplan

Datum	Sitzung	Referent/in	Literatur/Materialien
17.4.	Introduction and overview	Jan Snajder	Slides
24.4.	No session
1.5.	No session
8.5.	Student presentations	David Grimm	Hammarström and Borin (2011) (slides)
		Patrick Claus	Pirkola (2001), Kurimo et al. (2011) (slides)
15.5.	Student presentations	Julian Hitschler	Goldsmith (2001) (slides)
22.5.	Student presentations	Sabrina Mänz	Yarowsky and Wicentowski (2000), Yarowski et al. (2001) (slides)
29.5.	Student presentations	Felix Krauss	Schone and Jurafsky (2001) (slides)
		Isabell Wolter	Baroni et al. (2002) (slides)
5.6.	Student presentations	Madeline Remse	Creutz and Lagus (2002), Creutz and Lagus (2005) (slides)
12.6.	Student presentations	Lena Maldacker	Kazakov and Manandhar (2001) (slides)
19.6.	Student presentations	Atilla Azgin	Monson et al. (2008), Monson et al. (2009) (slides)
26.6.	Student presentations	Max Bacher	Majumder et al. (2007) (slides)
		Sven Feuchtmüller	Paik et al. (2011) (slides)
3.7.	Student presentations	Catarina Cramer	Poon et al. (2009) (slides)
10.7.	Student presentations	Chen Li	Naradowsky and Toutanova (2011)
17.7.	Student presentations	Leo Born	Xu and Croft (1998) (slides)
		Hans-Martin Ramsl	Dreyer and Eisner (2011) (slides)
24.7.	Student presentations and wrap-up	Angela Schneider	Can and Manandhar (2012)
	Wrap up	Jan Snajder	Slides

Literatur

Textbook:

• Brian Roark, Richard Sproat (2008). Computational Approaches to Morphology and Syntax. Oxford University Press.

Papers:

• Galvez, C. and de Moya-Anegon, F. and Solana, V.H. (2005). Term conflation methods in information retrieval: non-linguistic and linguistic approaches. Journal of Documentation, 61(4), pp. 520-547.
• Golsdsmith, J. (2001). Unsupervised learning of the morphology of a natural language . Computational Linguistics, 27(2), pp. 153-198.
• Hammarström, H. and Borin, L. (2011). Unsupervised learning of morphology . Computational Linguistics, 37(2), pp. 309-350.
• Karttunen, L. and Beesley, K.R. (2005). Twenty-five years of finite-state morphology . Inquiries Into Words, a Festschrift for Kimmo Koskenniemi on his 60th Birthday, pp. 71-83.
• Koskenniemi, K (1984). A general computational model for word-form recognition and production . Proceedings of the 10th international conference on Computational linguistics, pp. 178-181.
• Kurimo, M. and Virpioja, S. and Turunen, V. and Lagus, K. (2010). Morpho Challenge competition 2005-2010: Evaluations and results . Proceedings of the 11th Meething of the ACL Special Interest Group on Computational Morphology and Phonology, pp. 87-95.
• Pirkola, A. (2001). Morphological typology of languages for IR . Journal of Documentation, 57(3), pp. 330-358.

Weitere Literatur wird zu Beginn des Seminars bekanntgegeben.

» weitere Kursmaterialien