Research:

• German-English-Dutch resources and cognate translation
  • Revealing Phonological Similarities between Related Languages from Automatically Generated Parallel Corpora. In Proceedings of the ACL 2005 Workshop on Building and Using Parallel Texts: Data-Driven Machine Translation and Beyond , pp. 33-40, Ann Arbor, USA. (.pdf)
  • Revealing Phonological Similarities between German and Dutch. In Proceedings of Interspeech'2005 - Eurospeech: 9th European Conference on Speech Communication and Technology , pp. 1609-1612, Lissabon, Portugal. (.pdf)
• Automatically Revealing Phonological Similarities of Dutch and German, Talk at 15th Meeting of Computational Linguistics in the Netherlands (CLIN 2004).

• Topic of my dissertation
  
  • Probabilistic Syllable Modeling Using Unsupervised and Supervised Learning Methods.
    homepage of my PhD thesis

• Induction of syllable classes and application to a grapheme-to-phoneme (g2p) conversion task
  • Inducing Probabilistic Syllable Classes using Multivariate Clustering. With Bernd Möbius and Detlef Prescher. In Proceedings of the 38th Annual Meeting of the Association for Computational Linguistics (ACL 2000), Hong Kong, China. ( .ps / .ps.gz)
    
    
  • Inducing Probabilistic Syllable Classes using Multivariate Clustering - GOLD -. With Bernd Möbius and Detlef Prescher. In AIMS 6(4), IMS, Universität Stuttgart. ( .ps)
    
    Abstract:
    An approach to unsupervised learning and automatic detection of syllable structure is presented, using multi-dimensional EM-based clustering. The method yields phonologically meaningful syllable classes. These classes are shown to represent valuable input information in a grapheme-to-phoneme conversion task.
    
    

• Supervised method - German syllabification and PCFGs
  • Automatic Detection of Syllable Boundaries Combining the Advantages of Treebank and Bracketed Corpora Training. In Proceedings of the 39th Annual Meeting of the Association for Computational Linguistics (ACL 2001), Toulouse, France..ps) .
    
    Abstract:
    An approach to automatic detection of syllable boundaries is presented. We demonstrate the use of several manually constructed grammars trained with a novel algorithm combining the advantages of treebank and bracketed corpora training. We investigate the effect of the training corpus size on the performance of our system. The evaluation shows that a hand-written grammar performs better on finding syllable boundaries than does a treebank grammar.

• Unsupervised method - German syllabification and grapheme-to-phoneme conversion and PCFGs
  • Probabilistic Context-Free Grammars for Syllabification and Grapheme-to-Phoneme Conversion. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2001), Pittsburgh, PA..ps) .
    
    Abstract:
    We investigated the applicability of probabilistic context-free grammars to syllabifivation and grapheme-to-phoneme conversion. The results show that the standard probability model of context-free grammars performs very well in predicting syllable boundaries. However, our results indicate that the standard probability model does not solve grapheme-to-phoneme conversion sufficiently although, we varied all free parameters of the probabilistic reestimation procedure.
  
  
  • Silbifizierung im Deutschen mit Hilfe einer lexikalisierten probabilistischen kontextfreien Grammatik ( .ps) AIMS, Technical Report, University of Stuttgart, Institute of Natural Language Processing.

• Question answering for Dutch
  
  • Making Stone Soup: Evaluating a Recall-Oriented Multi-Stream Question
    Answering Stream for Dutch,
    With David Ahn, Valentin Jijkoun, Maarten de Rijke, Stefan Schlobach, and Gilad Mishne.
    In: Proceedings CLEF 2004, LNCS, Springer, 2005. (.pdf)
  • The University of Amsterdam at QA@CLEF 2004
    With Valentin Jijkoun, Gilad Mishne, Maarten de Rijke, Stefan Schlobach, David Ahn
    In: C. Peters and F. Borri, editors, Working Notes for the CLEF 2004 Workshop, pages 321-324, 2004. (.pdf)
  • A Recall Oriented Approach to Open Domain Question Answering (Abstract),
    With David Ahn, Valentin Jijkoun, Gilad Mishne, Maarten de Rijke, and Stefan Schlobach
    Poster at 15th Meeting of Computational Linguistics in the Netherlands (CLIN 2004).
  
  
• Question answering for English
  
  • The University of Amsterdam at TREC 2004,
    With David Ahn, Valentin Jijkoun, Jaap Kamps, Gilad Mishne, Maarten de Rijke, and Stefan Schlobach.
    In: TREC 2004 Conference Notebook, 2004. (.pdf)
  
  
• Named Entity Recognition
  
  • Using the Corpus Gesproken Nederlands to Build a Named Entity Recognizer.
    Christine Foeldesi, Karin Müller and Maarten de Rijke. Poster.
    Poster at the 14th Meeting of Computational Linguistics in the Netherlands,
  
  
• Building a question treebank
  
  • here you can find a homepage with resources.

• Stemming and Information Retrieval
  • The impact of stemming on information retrieval in Bahasa Indonesia (Abstract),
    With Fadillah Tala, Jaap Kamps, and Maarten de Rijke.
    In 14th Meeting of Computational Linguistics in the Netherlands (CLIN 2003), 2003.

• German word order and ordering principles in OVS and SVO sentences
  • Word order variation in German main clauses: A corpus analysis,
    With Andrea Weber. In the Proceedings of the 5th International Workshop on Linguistically Interpreted Corpora (LINC-04) in Geneva, Switzerland. (.pdf)
    
    
• Parsing with the TIGER corpus
  
  • Here is a suggestion for dividing the corpus into training and test corpus.

• Developing an unlexicalized probabilistic context-free Parser for German.
  • Experiments in German Treebank Parsing. With Sisay Fissaha, Daniel Olejnik, Ralf Kornberger, Detlef Prescher. In Proceedings of the 6th International Conference on Text, Speech and Dialogue (TSD-03), 8 pages. Ceske Budejovice, Czech Republic. (.pdf)

• Focus particles and how they influence intonation
  • German Focus Particles and Intonation. In Proceedings of the XIVth International Congress of Phonetic Sciences (ICPhS), San Francisco, August 1-7 1999
    
    
  • Master Thesis: German Focus Particles and their Influence on Intonation. Postscript(gz) University of Stuttgart, Institute of Natural Language Processing

• Secondary Thesis: Artikulatorische Realisierung von Akzent im Deutschen Postscript(gz), University of Stuttgart, Institute of Natural Language Processing