Introduction to Statistical Machine Translation
Instructor: Detlef Prescher
Date: Thursday, 11:30 a.m. - 1:00 p.m.
Location: SR 4, INF 327, Department of Computational Linguistics,
University of Heidelberg
First Lecture: Thursday, April 19, 2007
Announcements
2007-04-27: Course cancelled (Insufficient number of interested
students)
2007-04-19: Website published
Course Description
The course has three parts. In the first part, we follow an introduction to statistical machine translation (SMT) given by Kevin Knight at the JHU Summer Workshop in 1999. In the second part, we try to get an overview of techniques used in current SMT. For this, we simply follow lectures on SMT given by Philipp Koehn (2007), Empirical Methods in Natural Language Processing.
[See also the tutorials given by Kevin Knight and Philipp Koehn (2003), What's New in Statistical Machine Translation, and the ESSLLI course given by
Chris Callison-Burch and Philipp Koehn (2005), Introduction to Statistical Machine Translation.]
In the third part, students present some prominent papers on SMT.
Syllabus
April 19, 2007 - Slot 1
- Course description
April 26, 2007 - Slot 2
Crash course (I): Kevin Knight (1999),
A Statistical MT Tutorial Workbook. JHU Summer Workshop.
May 3, 2007 - Slot 3
- Crash course (II): Brown etal. (1993), The Mathematics of Statistical Machine Translation: Parameter Estimation
May 10, 2007 - Slot 4
- Discussion of assignments 1 and 2
May 17, 2007 - Christi Himmelfahrt
May 24, 2007 - Slot 5
- Philip Koehn (2007), Machine Translation (I): Introduction
May 31, 2007. Slot 6
- Philip Koehn (2007), Machine Translation (II): Word-based models and the EM algorithm
June 7, 2007. Fronleichnam
June 14. Slot 7
- Philip Koehn (2007), Machine Translation (III): Decoding
June 21, 2007. Slot 8
- Philip Koehn (2007), Machine Translation (IV): Phrase-based models
June 28, 2007. Slot 9
- Philip Koehn (2007), Machine Translation (V): Syntax-based models
July 5, 2007. Slot 10
- Philip Koehn (2007), Machine Translation (VI): Advanced topics
July 12, 2007. Slot 11
- Student presentation
Readings: Koehn et al. (2003), Statistical Phrase-Based Translation
July 12, 2007. Slot 12
- Student presentation
Readings: Yamada and Knight (2002),
A Syntax-Based Statistical Translation Model
July 12, 2007. Slot 13
- Student presentation
Readings: Collins etal. (2005),
Clause Restructuring for Statistical Machine Translation
Grading
Class participation (active/passive): 10%
Homeworks: 30%
Presentation: 60%
Links
Last updated: April 2007.
