Sciweavers

3140 search results - page 13 / 628
» On the Use of Comparable Corpora to Improve SMT performance
Sort
View
INTERSPEECH
2010
13 years 2 months ago
Fully automatic segmentation for prosodic speech corpora
While automatic methods for phonetic segmentation of speech can help with rapid annotation of corpora, most methods rely either on manually segmented data to initially train the p...
Sarah Hoffmann, Beat Pfister
IEEEPACT
2006
IEEE
14 years 1 months ago
Adaptive reorder buffers for SMT processors
In SMT processors, the complex interplay between private and shared datapath resources needs to be considered in order to realize the full performance potential. In this paper, we...
Joseph J. Sharkey, Deniz Balkan, Dmitry Ponomarev
ACL
2008
13 years 9 months ago
Exploiting N-best Hypotheses for SMT Self-Enhancement
Word and n-gram posterior probabilities estimated on N-best hypotheses have been used to improve the performance of statistical machine translation (SMT) in a rescoring framework....
Boxing Chen, Min Zhang, AiTi Aw, Haizhou Li
IJCNLP
2005
Springer
14 years 1 months ago
Empirical Study of Utilizing Morph-Syntactic Information in SMT
In this paper, we present an empirical study that utilizes morph-syntactical information to improve translation quality. With three kinds of language pairs matched according to mor...
Young-Sook Hwang, Taro Watanabe, Yutaka Sasaki
HPCA
2003
IEEE
14 years 8 months ago
Mini-Threads: Increasing TLP on Small-Scale SMT Processors
Several manufacturers have recently announced the first simultaneous-multithreaded processors, both as single CPUs and as components of multi-CPU chips. All are small scale, compr...
Joshua Redstone, Susan J. Eggers, Henry M. Levy