Sciweavers
Explore
Publications
Books
Software
Tutorials
Presentations
Lectures Notes
Datasets
Labs
Conferences
Community
Upcoming
Conferences
Top Ranked Papers
Most Viewed Conferences
Conferences by Acronym
Conferences by Subject
Conferences by Year
Tools
PDF Tools
Image Tools
Text Tools
OCR Tools
Symbol and Emoji Tools
On-screen Keyboard
Latex Math Equation to Image
Smart IPA Phonetic Keyboard
Community
Sciweavers
About
Terms of Use
Privacy Policy
Cookies
114
click to vote
EMNLP
2008
109
views
Natural Language Processing
»
more
EMNLP 2008
»
N-gram Weighting: Reducing Training Data Mismatch in Cross-Domain Language Model Estimation
15 years 4 months ago
Download
people.csail.mit.edu
In domains with insufficient matched training data, language models are often constructed by interpolating component models trained from partially matched corpora. Since the ngram...
Bo-June Paul Hsu, James R. Glass
claim paper
Read More »