Sciweavers

15375 search results - page 144 / 3075
» cans 2008
Sort
View
ACL
2008
13 years 9 months ago
Randomized Language Models via Perfect Hash Functions
We propose a succinct randomized language model which employs a perfect hash function to encode fingerprints of n-grams and their associated probabilities, backoff weights, or oth...
David Talbot, Thorsten Brants
ACL
2008
13 years 9 months ago
Learning Bilingual Lexicons from Monolingual Corpora
We present a method for learning bilingual translation lexicons from monolingual corpora. Word types in each language are characterized by purely monolingual features, such as con...
Aria Haghighi, Percy Liang, Taylor Berg-Kirkpatric...
ACL
2008
13 years 9 months ago
Phrase Table Training for Precision and Recall: What Makes a Good Phrase and a Good Phrase Pair?
In this work, the problem of extracting phrase translation is formulated as an information retrieval process implemented with a log-linear model aiming for a balanced precision an...
Yonggang Deng, Jia Xu, Yuqing Gao
ACL
2008
13 years 9 months ago
Integrating Graph-Based and Transition-Based Dependency Parsers
Previous studies of data-driven dependency parsing have shown that the distribution of parsing errors are correlated with theoretical properties of the models used for learning an...
Joakim Nivre, Ryan T. McDonald
ACL
2008
13 years 9 months ago
An Unsupervised Vector Approach to Biomedical Term Disambiguation: Integrating UMLS and Medline
This paper introduces an unsupervised vector approach to disambiguate words in biomedical text that can be applied to all-word disambiguation. We explore using contextual informat...
Bridget McInnes