Sciweavers

41 search results - page 8 / 9
» Linguistically Motivated Unsupervised Segmentation for Machi...
Sort
View
95
Voted
NAACL
2010
14 years 8 months ago
Extracting Parallel Sentences from Comparable Corpora using Document Level Alignment
The quality of a statistical machine translation (SMT) system is heavily dependent upon the amount of parallel sentences used in training. In recent years, there have been several...
Jason R. Smith, Chris Quirk, Kristina Toutanova
123
Voted
TASLP
2008
201views more  TASLP 2008»
14 years 10 months ago
Syntactically Lexicalized Phrase-Based SMT
Abstract--Until quite recently, extending Phrase-based Statistical Machine Translation (PBSMT) with syntactic knowledge caused system performance to deteriorate. The most recent su...
Hany Hassan, Khalil Sima'an, Andy Way
82
Voted
ANLP
1992
137views more  ANLP 1992»
14 years 11 months ago
Compound Nouns in a Unification-Based MT System
This paper describes an approach to the treatment of nominal compounds in a machine translation project employing a modern unification-based system. General problems connected wit...
Pierrette Bouillon, Katharina Boesefeldt, Graham R...
94
Voted
ACL
2010
14 years 8 months ago
Efficient Inference through Cascades of Weighted Tree Transducers
Weighted tree transducers have been proposed as useful formal models for representing syntactic natural language processing applications, but there has been little description of ...
Jonathan May, Kevin Knight, Heiko Vogler
191
Voted
ALT
2011
Springer
13 years 10 months ago
On the Expressive Power of Deep Architectures
Deep architectures are families of functions corresponding to deep circuits. Deep Learning algorithms are based on parametrizing such circuits and tuning their parameters so as to ...
Yoshua Bengio, Olivier Delalleau