See How Your Research Aligns
Create a free account to analyze your research alignment,
identify potential research gaps, and generate personalized
application documents for this professor.
Create Free Account
David Yarowsky
Word Sense Disambiguation
Minimally Supervised Induction Algorithms
Natural Language Processing (NLP)
Multilingual Natural Language Processing
About
David Yarowsky is a professor of computer science, the director of the Low-Resource Languages Lab, and a member of the Center for Language and Speech Processing at the Johns Hopkins University. His research focuses on word sense disambiguation, minimally supervised induction algorithms in natural language processing, and multilingual NLP.
Yarowsky earned his bachelor’s (1987) in computer science at Harvard University and his master’s (1993) and PhD (1996) in computer and information science at the University of Pennsylvania.
Research Performance Summary
1992-2025
Active Research Span
First Recorded Paper
Word-sense disambiguation using statistical models of Roget’s categories trained on large corpora
Year:
1992
Citations:
1206
Venue:
COLING 1992 Volume 2: The 14th International Conference on Computational
Latest Recorded Paper
JHU IWSLT 2025 Low-resource System Description
Year:
2025
Citations:
1
Venue:
Proceedings of the 22nd International Conference on Spoken Language
Last 10 Years Publication Activity
This timeline shows the professor's yearly publication activity.
Publication Venues and Collaboration
Journal, Conference, and Book Publication Breakdown
Top Coauthors
Yarowsky
Church
Research Impact by Period
Papers
6
Citations
94
Avg. Citations / Paper
15.7
H-Index
3
Papers
20
Citations
417
Avg. Citations / Paper
20.9
H-Index
10
Papers
28
Citations
1706
Avg. Citations / Paper
60.9
H-Index
16
Papers
23
Citations
2119
Avg. Citations / Paper
92.1
H-Index
16
Papers
26
Citations
826
Avg. Citations / Paper
31.8
H-Index
16
Papers
31
Citations
3136
Avg. Citations / Paper
101.2
H-Index
20
Papers
20
Citations
6088
Avg. Citations / Paper
304.4
H-Index
14
Papers
12
Citations
5076
Avg. Citations / Paper
423
H-Index
10
Contact and Professional Links
Detected Research Keywords
Word Sense Disambiguation
Statistical Machine Translation
Robust Projection Across
Projection Across Aligned
Across Aligned Corpora
Natural Language Processing
Inducing Multilingual Pos
Multilingual Pos Taggers
Pos Taggers Np
Taggers Np Bracketers