A simple term extractor interface giving easy access to terminology extraction functionality.
Translators can make use of many features of Sketch Engine related term extraction, translation lookup, grammar and usage checking.
Term extraction for translators
Translators can easily fill their CAT tool term base with terminology for maintaining consistency and quality across all translation jobs from the same area or the same client. Sketch Engine’s sophisticated term extraction or bilingual term extraction uses state-of-the-art natural language processing know-how to identify terminology. Statistical analysis is aided by comparing the use of words in the user’s text to their use in a large multi-billion word corpus of general text. The results include both single- and multi-word units and can be exported into your CAT tool in a widely supported TBX format.
Term extraction for interpreters
You can prepare for your interpreting job even if the client did not provide any supporting materials. You can have Sketch Engine search the internet for you and download texts related to the topic you specify. Then use the term extraction feature to extract terminology. This process can be repeated many times to create a large domain-specific corpus and extract as many terms as needed.
Get inspiration from other translators. Use parallel corpora to look up translations of words or phrases as they were translated by others and chose the option that fits your context best. Useful especially for idiomatic expressions or any other situations when bilingual dictionaries fail to provide a solution.
Grammar and usage checking
Use the concordance feature to find examples of the word or phrase in context and see how it is used by real users of the language. Compare how frequently different alternatives appear in the corpus to assess which is the most natural to use in your context.
Use Word Sketch for any high-frequency expressions to get a one-page overview of words frequently used together with the word. The collocations are sorted according to grammatical categories such as modifiers, objects of verbs etc. for easy use.
Alternative word suggestions
A printed thesaurus is always limited by space. The automatic distributional thesaurus in Sketch Engine can provide synonyms, antonyms and related words for almost any word in a language (provided the corpus is large enough to contain enough occurrences of the word but Sketch Engine contains some of the biggest corpora in many languages). Use the thesaurus to quickly view alternatives of the word you are about to use.
Additional content for the term base
Upload your translation memory and use n-grams to identify multi-word expressions which may not be normally labelled as terms but frequently appear in the texts you translate. Some examples in English might be as a matter of fact, at the beginning of etc. Add them to your term base to have them translated automatically by your CAT tool.
Marco Baroni, Kilgarriff, Jan Pomikálek and Pavel Rychlý (2006). WebBootCaT: instant domain-specific corpora to support human translators. In Proceedings of EAMT. 11th Annual Conference of the European Association for Machine Translation. Norway, pp. 247–252.