Search results
Results From The WOW.Com Content Network
A number of computer-assisted translation software and websites exists for various platforms and access types. According to a 2006 survey undertaken by Imperial College of 874 translation professionals from 54 countries, primary tool usage was reported as follows: Trados (35%), Wordfast (17%), Déjà Vu (16%), SDL Trados 2006 (15%), SDLX (4%), STAR Transit [fr; sv] (3%), OmegaT (3%), others (7%).
The following table compares the number of languages which the following machine translation programs can translate between. (Moses and Moses for Mere Mortals allow you to train translation models for any language pair, though collections of translated texts (parallel corpus) need to be provided by the user.
Neural machine translation (NMT) is an approach to machine translation that uses an artificial neural network to predict the likelihood of a sequence of words, typically modeling entire sentences in a single integrated model.
BLEU was one of the first metrics to report a high correlation with human judgments of quality. The metric is currently one of the most popular in the field. The central idea behind the metric is that "the closer a machine translation is to a professional human translation, the better it is". [8]
GNMT's proposed architecture of system learning was first tested on over a hundred languages supported by Google Translate. [2] With the large end-to-end framework, the system learns over time to create better, more natural translations. [1] GNMT attempts to translate whole sentences at a time, rather than just piece by piece. [1]
Although Google has deployed a new system called neural machine translation for better quality translation, there are languages that still use the traditional translation method called statistical machine translation. It is a rule-based translation method that uses predictive algorithms to guess ways to translate texts in foreign languages.
These tools allow for the extraction of terminology and for checking for the consistent use of terminology. The tools allow for checking for various technical errors such as the correct use of variables. Lastly, the toolkit provides a powerful localisation API [2] that acts as a base on which to build other localization related tools.
OmegaT is another translation tool that can translate PO files. It is written in Java so it is available for multiple platforms (including Linux and Windows). It can be downloaded from SourceForge. GNU Gettext (Linux/Unix) used for the GNU Translation Project. Gettext also provides msgmerge that makes merging translations easy.