686 search results - page 39 / 138 » Minimax Probability Machine |
117
click to vote
EMNLP
2009
14 years 10 months ago
2009
We present a new phrase-based conditional exponential family translation model for statistical machine translation. The model operates on a feature representation in which sentenc...
108
click to vote
ACL
2006
15 years 2 months ago
2006
Sentence compression is a task of creating a short grammatical sentence by removing extraneous words or phrases from an original sentence while preserving its meaning. Existing me...
95
Voted
NIPS
2001
15 years 2 months ago
2001
Partial information can trigger a complete memory. At the same time, human memory is not perfect. A cue can contain enough information to specify an item in memory, but fail to tr...
101
click to vote
EMNLP
2009
14 years 10 months ago
2009
Tree Adjoining Grammars have well-known advantages, but are typically considered too difficult for practical systems. We demonstrate that, when done right, adjoining improves tran...
78
Voted
COLING
2010
14 years 7 months ago
2010
Traditional 1-best translation pipelines suffer a major drawback: the errors of 1best outputs, inevitably introduced by each module, will propagate and accumulate along the pipeli...