Sciweavers

3140 search results - page 18 / 628
» On the Use of Comparable Corpora to Improve SMT performance
Sort
View
COLING
2010
13 years 2 months ago
Discriminative Induction of Sub-Tree Alignment using Limited Labeled Data
We employ Maximum Entropy model to conduct sub-tree alignment between bilingual phrasal structure trees. Various lexical and structural knowledge is explored to measure the syntac...
Jun Sun, Min Zhang, Chew Lim Tan
DSN
2007
IEEE
14 years 2 months ago
BlackJack: Hard Error Detection with Redundant Threads on SMT
Testing is a difficult process that becomes more difficult with scaling. With smaller and faster devices, tolerance for errors shrinks and devices may act correctly under certain ...
Ethan Schuchman, T. N. Vijaykumar
HIPEAC
2007
Springer
14 years 1 months ago
Dynamic Capacity-Speed Tradeoffs in SMT Processor Caches
Caches are designed to provide the best tradeoff between access speed and capacity for a set of target applications. Unfortunately, different applications, and even different phas...
Sonia López, Steve Dropsho, David H. Albone...
ICDM
2008
IEEE
80views Data Mining» more  ICDM 2008»
14 years 2 months ago
Collective Latent Dirichlet Allocation
In this paper, we propose a new variant of Latent Dirichlet Allocation(LDA): Collective LDA (C-LDA), for multiple corpora modeling. C-LDA combines multiple corpora during learning...
Zhiyong Shen, Jun Sun, Yi-Dong Shen
CICLING
2008
Springer
13 years 9 months ago
Evaluation of Internal Validity Measures in Short-Text Corpora
Short texts clustering is one of the most difficult tasks in natural language processing due to the low frequencies of the document terms. We are interested in analysing these kind...
Diego Ingaramo, David Pinto, Paolo Rosso, Marcelo ...