PROMT (from PROject MT — the project of machine translation) is a Russian company focused upon the development of machine translation systems. At the moment PROMT translators exist for English, German, French, Spanish, Italian, Portuguese and Russian languages. PROMT is headquartered in Saint Petersburg, Russia and also has offices in Moscow, Russia, San Francisco, the USA and Hamburg, Germany. Except the system of machine translation PROMT also delivers its own solutions on the basis of the Translation memory technology.
PROMT translation is a rule-based machine translation (RBMT). RBMT is a machine translation system based on linguistic information about source and target languages basically retrieved from (bilingual) dictionaries and grammars covering the main semantic, morphological, and syntactic regularities of each language respectively. Having input sentences (in some source language), an RBMT system generates them to output sentences (in some target language) on the basis of morphological, syntactic, and semantic analysis of both the source and the target languages involved in a concrete translation task.
At the end of 2010 of PROMT provided the Hybrid technology of translation leverages the strengths of Statistical machine translation and rule-based translation methodologies. The approaches differ in a number of ways:
Rules post-processed by statistics: Translations are performed using a rules based engine. Statistics are then used in an attempt to adjust/correct the output from the rules engine.
Statistics guided by rules: Rules are used to pre-process data in an attempt to better guide the statistical engine. Rules are also used to post-process the statistical output to perform functions such as normalization. This approach has a lot more power, flexibility and control when translating.