Sciweavers

70 search results - page 6 / 14
» Machine Translation without a source text
Sort
View
EMNLP
2009
13 years 4 months ago
Discriminative Corpus Weight Estimation for Machine Translation
Current statistical machine translation (SMT) systems are trained on sentencealigned and word-aligned parallel text collected from various sources. Translation model parameters ar...
Spyros Matsoukas, Antti-Veikko I. Rosti, Bing Zhan...
ACL
2006
13 years 8 months ago
A Phrase-Based Statistical Model for SMS Text Normalization
Short Messaging Service (SMS) texts behave quite differently from normal written texts and have some very special phenomena. To translate SMS texts, traditional approaches model s...
AiTi Aw, Min Zhang, Juan Xiao, Jian Su
LREC
2008
174views Education» more  LREC 2008»
13 years 8 months ago
Evaluation of a Machine Translation System for Low Resource Languages: METIS-II
In this paper we describe the METIS-II system and its evaluation on each of the language pairs: Dutch, German, Greek, and Spanish to English. The METIS-II system envisaged develop...
Vincent Vandeghinste, Peter Dirix, Ineke Schuurman...
EMNLP
2008
13 years 8 months ago
Language and Translation Model Adaptation using Comparable Corpora
Traditionally, statistical machine translation systems have relied on parallel bi-lingual data to train a translation model. While bi-lingual parallel data are expensive to genera...
Matthew G. Snover, Bonnie J. Dorr, Richard M. Schw...
COLING
1992
13 years 8 months ago
The Kant System: Fast, Accurate, High-Quality Translation In Practical Domains
Knowledge-based interlingual machine translation systems produce semantically accurate translations, but typically require massive knowledge acquisition. Ongoing research and deve...
Eric Nyberg, Teruko Mitamura