Sciweavers

577 search results - page 10 / 116
» Improved Text Generation Using N-gram Statistics
Sort
View
ICASSP
2010
IEEE
14 years 10 months ago
Improved statistical models for SMT-based speaking style transformation
Automatic speech recognition (ASR) results contain not only ASR errors, but also disfluencies and colloquial expressions that must be corrected to create readable transcripts. We...
Graham Neubig, Yuya Akita, Shinsuke Mori, Tatsuya ...
WWW
2006
ACM
15 years 3 months ago
Do not crawl in the DUST: different URLs with similar text
We consider the problem of dust: Different URLs with Similar Text. Such duplicate URLs are prevalent in web sites, as web server software often uses aliases and redirections, and...
Uri Schonfeld, Ziv Bar-Yossef, Idit Keidar
ACL
1998
14 years 11 months ago
A Simple Hybrid Aligner for Generating Lexical Correspondences in Parallel Texts
We present an algorithm for bilingual word alignment that extends previous work by treating multi-word candidates on a par with single words, and combining some simple assumptions...
Lars Ahrenberg, Mikael Andersson, Magnus Merkel
CSL
2011
Springer
14 years 5 months ago
Syntax-based reordering for statistical machine translation
In this paper we address the problem of translating between languages with word order disparity. The idea of augmenting statistical machine translation (SMT) by using a syntax-bas...
Maxim Khalilov, José A. R. Fonollosa
CIARP
2007
Springer
15 years 4 months ago
A Statistical User Simulation Technique for the Improvement of a Spoken Dialog System
Abstract. In this paper, we present a statistical approach for the automatic generation of dialogs by means of a user simulator. This technique can be used to generate dialogs with...
Lluís Hurtado, David Griol, Emilio Sanchis,...