Kirk Baker, PhD
| The Ohio State University, 2008 Department of Linguistics
|
LinkedIn: http://www.linkedin.com/in/bakerkirk
Specialization
Statistical Language Processing; Text Mining; Computational Lexical Semantics; Machine Learning; Scalable NLP Systems
Current Employment
I work for Collexis, Inc., a Columbia, South Carolina-based company specializing in vertical
search and knowledge discovery software. I currently work full-time on a text classification project
called the Research, Condition, and Disease Categorization Project (RCDC) at
the National Institutes of Health.
Data
English-Korean Transliteration List [Please cite as: Baker, Kirk. 2008. English-Korean
Transliteration List (v0.1). Electronic document. http://purl.oclc.org/net/kbaker/data]
Papers
- Multilingual Animacy Classification by Sparse Logistic Regression
- Lettered Words: Using Roman Letters to Create Words in Chinese
- An Interactive Automatic Document Classification Prototype
Kirk Baker,
Archna Bhandari and Rao Thotakura
Proceedings of the Third Workshop on Human-Computer Interaction and Information Retrieval. Washington, D.C. October 23, 2009.
- Statistical Identification of English Loanwords in Korean Using Automatically Generated Training Data
- Singular Value Decomposition Tutorial
Kirk Baker
Electronic document. 2005.
- Production and perception of glottalized vowels in Coatzospan Mixtec
- Constraining user response via multimodal dialog interface
- Prosodic structure and perception of Korean domain-initial coronal stops
Kirk Baker
International Journal of Korean Linguistics. 11:119-132. 2002.
-
Semantic and Dialogic Annotation for Automated Multilingual Customer Service
- Multi-layer Dialogue Annotation for Automated Multilingual Customer Service
-
Segmental and Prosodically-Governed Delateralization
Soo Jung Kim and Kirk Baker
In Harvard Studies in Korean Linguistics VIII, S. Kuno et al. eds. Cambridge, MA: Harvard University, 152–166, 1999.
Dissertation: Multilingual Distributional Lexical Similarity