Word-level machine translation

Translate Words translates between any pair of 58 available languages, enabling multi-language analysis without full text-level translation.

Zafer Çavdar avatar
Written by Zafer Çavdar
Updated over a week ago

Keywords: machine translation, word translation

While full-text machine translation most accurately translates documents, it can be expensive and time-consuming for large volumes of text. A fast and free alternative is to translate individual words that have been extracted from the text. This is what the Translate Words operation does.

The operation covers 58 languages and can translate between any pair of these languages. When documents in multiple languages are present in a dataset, a language field can be specified to translate from the correct language for each document.

If an input value contains more than a single word, it is split into individual words, which are then translated individually and joined together in the same order.

Step-by-step guide

1. Open the operation configuration window

Select the field with the words that you want to translate and click the "Add operation" button at the top of the workspace. (If you have not already tokenized your text into words, do so by using the Tokenize & Tag operation).

Search for "Word Translation" or find the operation under "Text Enrichment" and click it.

2. Name the output field

Under "Output field name", type the name of the output field.

3. Specify the source language

Under "Source language", select the language that you want to translate from.

4. Specify target language

Under "Target language", select the language you want to translate to.

5. Apply the operation

Click "Apply" to run the operation. The translated words are inserted into the output field.

Did this answer your question?