577 search results - page 1 / 116 » Improved Text Generation Using N-gram Statistics |
IBERAMIA
2010
Springer
13 years 2 months ago
2010
Springer
Abstract. In Natural Language Generation (NLG) systems, a generalpurpose surface realisation module will usually require the underlying application to provide highly detailed input...
EMNLP
2009
13 years 2 months ago
2009
Untranslated words still constitute a major problem for Statistical Machine Translation (SMT), and current SMT systems are limited by the quantity of parallel training texts. Augm...
EACL
2009
ACL Anthology
13 years 2 months ago
2009
ACL Anthology
like text summarisation requires a means of producing novel summary sentences. In order to improve the grammaticality of the generated sentence, we model a global (sentence) level...
ICALT
2010
IEEE
13 years 5 months ago
2010
IEEE
In this study I use statistical Natural Language Processing and adapted Controlled Language methods to preprocess individual documents before they are used as source documents for ...
NLE
2007
13 years 3 months ago
2007
We address the problem of extracting bilingual chunk pairs from parallel text to create training sets for statistical machine translation. We formulate the problem in terms of a s...