Sciweavers

66 search results - page 2 / 14
» mt 2010
Sort
View
AAAI
2010
13 years 5 months ago
Multi-Task Sparse Discriminant Analysis (MtSDA) with Overlapping Categories
Multi-task learning aims at combining information across tasks to boost prediction performance, especially when the number of training samples is small and the number of predictor...
Yahong Han, Fei Wu, Jinzhu Jia, Yueting Zhuang, Bi...
MT
2010
88views more  MT 2010»
13 years 3 months ago
Metric and reference factors in minimum error rate training
In Minimum Error Rate Training (MERT), BLEU is often used as the error function, despite the fact that it has been shown to have a lower correlation with human judgment than other...
Yifan He, Andy Way
MT
2010
96views more  MT 2010»
13 years 3 months ago
Monte Carlo techniques for phrase-based translation
Recent advances in statistical machine translation have used approximate beam search for NP-complete inference within probabilistic translation models. We present an alternative ap...
Abhishek Arun, Barry Haddow, Philipp Koehn, Adam L...
MT
2010
100views more  MT 2010»
13 years 3 months ago
Exploiting syntactic relationships in a phrase-based decoder: an exploration
Phrase-based decoding is conceptually simple and straightforward to implement, at the cost of drastically oversimplified reordering models. Syntactically aware models make it pos...
Tim Hunter, Philip Resnik
ICTAI
2010
IEEE
13 years 3 months ago
Support Vector Methods for Sentence Level Machine Translation Evaluation
Recent work in the field of machine translation (MT) evaluation suggests that sentence level evaluation based on machine learning (ML) can outperform the standard metrics such as B...
Antoine Veillard, Elvina Melissa, Cassandra Theodo...