Sciweavers

577 search results - page 13 / 116
» Improved Text Generation Using N-gram Statistics
Sort
View
NAACL
2010
14 years 7 months ago
Improving Phrase-Based Translation with Prototypes of Short Phrases
We investigate methods of generating additional bilingual phrase pairs for a phrasebased decoder by translating short sequences of source text. Because our translation task is mor...
Frank Liberato, Behrang Mohit, Rebecca Hwa
ETS
2007
IEEE
110views Hardware» more  ETS 2007»
15 years 4 months ago
Analyzing Volume Diagnosis Results with Statistical Learning for Yield Improvement
— A novel statistical learning algorithm is proposed to accurately analyze volume diagnosis results. This algorithm effectively overcomes the inherent ambiguities in logic diagno...
Huaxing Tang, Manish Sharma, Janusz Rajski, Martin...
ICASSP
2009
IEEE
15 years 1 months ago
From rule-based to statistical grammars: Continuous improvement of large-scale spoken dialog systems
Statistical Spoken LanguageUnderstandinggrammars (SSLUs) are often used only at the top recognition contexts of modern large-scale spoken dialog systems. We propose to use SSLUs a...
David Suendermann, Keelan Evanini, Jackson Liscomb...
COLING
2002
14 years 9 months ago
The Computation of Word Associations: Comparing Syntagmatic and Paradigmatic Approaches
It is shown that basic language processes such as the production of free word associations and the generation of synonyms can be simulated using statistical models that analyze th...
Reinhard Rapp
ECAI
2004
Springer
15 years 3 months ago
Lessons from Deploying NLG Technology for Marine Weather Forecast Text Generation
SUMTIME-MOUSAM is a Natural Language Generation (NLG) system that produces textual weather forecasts for offshore oilrigs from Numerical Weather Prediction (NWP) data. It has been ...
Somayajulu Sripada, Ehud Reiter, Ian Davy, Kristia...