Kristina Toutanova
 

 

 

Publications and Presentations

I was a PhD student in Computer Science at Stanford, advised by Chris Manning. I am currently a researcher in the NLP group at Microsoft Research.
E-mail: MyFirstName@cs.stanford.edu

Research Interests


I am interested in a broad range of problems in Natural Language Processing. I focus on developing machine learning algorithms suitable for natural language disambiguation tasks.

Topics I have worked on include: statistical machine translation, syntactic parsing, semantic role labeling, smoothing for lexical distributions, part-of-speech tagging, alignment for statistical machine translation, text categorization, spelling correction, natural language generation, and word sense disambiguation.

Recent Publications

 

Scott Yih and Kristina Toutanova, 2006. Automatic Semantic Role Labeling. (pdf)HLT-NAACL 2006 tutorial.

 

Kristina Toutanova. 2006. Competitive generative models with structure learning for NLP classification tasks.To appear in EMNLP 2006.

 

Hisami Suzuki and Kristina Toutanova. 2006. Learning to predict case markers in Japanese. To appear in COLING-ACL 2006.

 

Kristina Toutanova, 2005 .New! PhD Thesis Stanford, 2005.

 

Kristina Toutanova, Aria Haghighi, and Christopher D. Manning. 2005 .Joint learning improves semantic role labeling. ACL 2005.

 

Rajat Raina, Aria Haghighi, Christopher Cox, Jenny Finkel, Jeff Michels, Kristina Toutanova, Bill MacCartney, Marie-Catherine de Marneffe, Christopher D. Manning, and Andrew Y. Ng. 2005. Robust Textual Inference using Diverse Knowledge Sources. First PASCAL Challenges Workshop.

 

Aria Haghighi, Kristina Toutanova, and Christopher D. Manning. 2005 .A Joint Model for Semantic Role Labeling. CoNLL 2005 Shared Task.

 

Kristina Toutanova, Christopher D. Manning, Dan Flickinger, and Stephan Oepen. 2005 .Stochastic HPSG Parse Disambiguation using the Redwoods Corpus. To appear in Journal of Logic and Computation 2005.

 

Kristina Toutanova, Christopher D. Manning, and Andrew Y. Ng. 2004 .Learning Random Walk Models for Inducing Word Dependency Distributions. In Proceedings of ICML 2004.

 

Kristina Toutanova, Penka Markova, and Christopher D. Manning. 2004. The Leaf Projection Path View of Parse Trees: Exploring String Kernels for HPSG Parse Selection In Proceedings of EMNLP 2004.

 

Kristina Toutanova, Dan Klein, Christopher D. Manning, and Yoram Singer. 2003.Feature-Rich Part-of-Speech Tagging with a Cyclic Dependency Network. In Proceedings of HLT-NAACL 2003 pages 252-259.

 

Kristina Toutanova, Mark Mitchell and Christopher D. Manning. 2003.Optimizing Local Probability Models for Statistical Parsing. In Proceedings of 14th European Conference on Machine Learning(ECML 2003). [best student paper runner-up award]

 

Kristina Toutanova and Robert C. Moore. 2002. Pronunciation Modeling for Improved Spelling Correction. In Proceedings of the 40th Meeting of the Association for Computational Linguistics(ACL-2002) pages 141-151.

 

Kristina Toutanova and H. Tolga Ilhan and Christopher D. Manning. 2002. Extensions to HMM-based Statistical Word Alignment Models. In Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing(EMNLP-2002) pages 87-94.

 

Kristina Toutanova and Christopher D. Manning. 2002. Feature Selection for a Rich HPSG Grammar Using Decision Trees.Proceedings of the Sixth Conference on Natural Language Learning(CoNLL-2002)Taipei, Taiwn

 

Kristina Toutanova, Christopher D. Manning, Stuart M. Shieber, Dan Flickinger, and Stephan Oepen. 2002. Parse Disambiguation for a Rich HPSG Grammar. First Workshop on Treebanks and Linguistic Theories (TLT2002), pp. 253-263.

 

Stephan Oepen, Kristina Toutanova, Stuart Shieber, Christopher D. Manning, Dan Flickinger, and Thorsten Brants. 2002. The LinGO Redwoods Treebank: Motivation and Preliminary Applications. Proceedings of the 19th International Conference on Computational Linguistics (COLING 2002).

 

Kristina Toutanova, Francine Chen, Kris Popat, and Thomas Hofmann Text Classification in a Hierarchical Mixture Model for Small Training Sets. Proceedings of the Tenth International ACM Conference on Information and Knowledge Management, CIKM 2001.

 

Kristina Toutanova and Christopher D. Manning. Enriching the Knowledge Sources Used in a Maximum Entropy Part-of-Speech Tagger. Proceedings of the Joint SIGDAT Conference on Empirical Methods in Natural Language Processing and Very Large Corpora (EMNLP/VLC-2000), Hong Kong.

 

Pavlin Dobrev, Kristina Toutanova: CGWorld -- a Web Based Workbench for Conceptual Graphs Management and Applications. ICCS 2000.

 

Presentations

Some of my presentations are available here.

 

Learning Random Walk Models for Inducing Word Dependency Distributions (ppt) Presented at ICML 2004.

 

The Leaf Projection Path View of Parse Trees: Exploring String Kernels for HPSG Parse Selection (ppt) Presented at EMNLP 2004.

 

Feature-Rich Part-of-Speech Tagging with a Cyclic Dependency Network (ppt) Presented at HLT-NAACL 2003.

 

Optimizing Local Probability Models for Statistical Parsing (ppt) Presented at ECML 2003.

 

Generative and Discriminative Models in NLP: A Survey (ppt) Presented at the Stanford Seminar on Computational Learning and Adaptation, November 2002.

About me

 

I am from Bulgaria, one of the most beautiful countries in the world.

Here is information about Bulgaria:

All About Bulgaria

 

my sister and I

with my sister and two nieces

family

            I am taking dance classes with the Stanford Ballroom Dance Team, and I recommend them to everyone.