Department information

 

Reading Group: Statistical Methods in Multilingual Information Access

Time: every second Thursday at 10-12 Place: A307

Description

In the reading group, state-of-the art statistical methods in multilingual information access are studied. Problem domains of interest include statistical machine translation (SMT) and cross-language information retrieval (CLIA), and the probabilistic modeling and machine learning techniques that can be used in solving these problems. The reading group is related to the EU project SMART (Statistical Multilingual Analysis for Retrieval and Translation). The following topics are of interest:

• feature representations for natural language,
• alignment/translation models,
• language models/translation fluency,
• Markov models for SMT,
• statistical parsing,
• structured output learning
• latent semantic representations for natural language,
• probabilistic and language models for information retrieval.

Participants

Wray Buntine, Mätti Kääriäinen, Petri Myllymäki, Jussi Piitulainen, Juho Rousu, Marko Salmenkivi, Ville Tuulos, Kimmo Valtonen, Matti Vuorinen, Roman Yangarber, Huizhen (Janey) Yu

Forms

For each meeting, we have a selected paper that everyone is expected to read before the meeting. In addition, one of the participants will be the reader, 'esilukija', who will guide us through the paper. Note that everybody is expected to have read the paper :)

Schedule

• Thu 16.10 Paper: R. Kneser and H. Ney: Improved backing-off for m-gram language modeling In Proc. of the IEEE International Conference on Acoustics, Speech and Signal Processing, volume 1, pages 181--184, 1995. Reader: Matti K.
• Thu 2.11 Paper: P. E Brown, V.J. Della Pietra, S.A. Della Pietra, Robert L. Mercer: The Mathematics of Statistical Machine Translation: Parameter Estimation Computational Linguistics, Volume 19, Number 1, March 1993. Reader: Janey
• Thu 16.11 We continue with Brown et al...
• Thu 30.11 Paper:
  • Philipp Koehn, Franz Josef Och, Daniel Marcu. Statistical Phrase-Based Translation. In Proceedings of the Human Language Technology Conference 2003 (HLT-NAACL 2003), Edmonton, Canada, May 2003.
  • Franz Josef Och. Minimum Error Rate Training for Statistical Machine Translation. In "ACL 2003: Proc. of the 41st Annual Meeting of the Association for Computational Linguistics", Japan, Sapporo, July 2003.
• Thu 25.1.07 Paper: C. Cortes, M. Mohri, J. Weston: A general regression technique for learning transductions. ICML'2005, pp. 153 - 160 Reader: Juho

Literature

To be extended...

• T.L. Griffiths and M. Steyvers, "Finding scientific topics," PNAS Colloquium, 2004.
• D. Klein and C.D. Manning, "Corpus-based induction of syntactic structure: Models of dependency and constituency," ACL, pages 478-485, 2004.
• C. Sutton and A. McCallum, "An Introduction to Conditional Random Fields," in Relational Learning. In Introduction to Statistical Relational Learning, Edited by L. Getoor and B. Taskar. MIT Press. 2006.
• B. Taskar, D. Klein, M. Collins, D. Koller, and C. Manning, "Max-margin parsing," in Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2004.

• C.D. Manning and H. Schutze. Foundations of Statistical Natural Language Processing. MIT Press, 1999.
• R. Baeza-Yates and B. Ribeiro-Neto. Modern Information Retrieval. Addison Wesley, 1999.
• The Association for Computational Linguistics website.
• Statistical natural language processing and corpus-based computational linguistics: An annotated list of resources webite.