Class LanguageTranslatorV3

Uploads training files to customize a translation model. You can customize a model with a forced glossary or with a parallel corpus:

• Use a forced glossary to force certain terms and phrases to be translated in a specific way. You can upload only a single forced glossary file for a model. The size of a forced glossary file for a custom model is limited to 10 MB.
• Use a parallel corpus when you want your custom model to learn from general translation patterns in parallel sentences in your samples. What your model learns from a parallel corpus can improve translation results for input text that the model has not been trained on. You can upload multiple parallel corpora files with a request. To successfully train with parallel corpora, the corpora files must contain a cumulative total of at least 5000 parallel sentences. The cumulative size of all uploaded corpus files for a custom model is limited to 250 MB.

Depending on the type of customization and the size of the uploaded files, training time can range from minutes for a glossary to several hours for a large parallel corpus. To create a model that is customized with a parallel corpus and a forced glossary, customize the model with a parallel corpus first and then customize the resulting model with a forced glossary.

You can create a maximum of 10 custom models per language pair. For more information about customizing a translation model, including the formatting and character restrictions for data files, see Customizing your model.

Supported file formats

You can provide your training data for customization in the following document formats:

• TMX (.tmx) - Translation Memory eXchange (TMX) is an XML specification for the exchange of translation memories.
• XLIFF (.xliff) - XML Localization Interchange File Format (XLIFF) is an XML specification for the exchange of translation memories.
• CSV (.csv) - Comma-separated values (CSV) file with two columns for aligned sentences and phrases. The first row must have two language codes. The first column is for the source language code, and the second column is for the target language code.
• TSV (.tsv or .tab) - Tab-separated values (TSV) file with two columns for aligned sentences and phrases. The first row must have two language codes. The first column is for the source language code, and the second column is for the target language code.
• JSON (.json) - Custom JSON format for specifying aligned sentences and phrases.
• Microsoft Excel (.xls or .xlsx) - Excel file with the first two columns for aligned sentences and phrases. The first row contains the language code.

You must encode all text data in UTF-8 format. For more information, see Supported document formats for training data.

Specifying file formats

You can indicate the format of a file by including the file extension with the file name. Use the file extensions shown in Supported file formats.

Alternatively, you can omit the file extension and specify one of the following content-type specifications for the file:

• TMX - application/x-tmx+xml
• XLIFF - application/xliff+xml
• CSV - text/csv
• TSV - text/tab-separated-values
• JSON - application/json
• Microsoft Excel - application/vnd.openxmlformats-officedocument.spreadsheetml.sheet

For example, with curl, use the following content-type specification to indicate the format of a CSV file named glossary:

--form "forced_glossary=@glossary;type=text/csv".

Deletes a document.

Deletes a custom translation model.

Gets the translation status of a document.

Gets information about a translation model, including training status for custom models. Use this API call to poll the status of your customization request. A successfully completed training has a status of available.

Gets the translated document associated with the given document ID.

Identifies the language of the input text.

Lists documents that have been submitted for translation.

Lists the languages that the service can identify. Returns the language code (for example, en for English or es for Spanish) and name of each language.

Lists all supported languages for translation. The method returns an array of supported languages with information about each language. Languages are listed in alphabetical order by language code (for example, af, ar). In addition to basic information about each language, the response indicates whether the language is supported_as_source for translation and supported_as_target for translation. It also lists whether the language is identifiable.

Lists available translation models.

Translates the input text from the source language to the target language. Specify a model ID that indicates the source and target languages, or specify the source and target languages individually. You can omit the source language to have the service attempt to detect the language from the input text. If you omit the source language, the request must contain sufficient input text for the service to identify the source language.

You can translate a maximum of 50 KB (51,200 bytes) of text with a single request. All input text must be encoded in UTF-8 format.

Submit a document for translation. You can submit the document contents in the file parameter, or you can reference a previously submitted document by document ID. The maximum file size for document translation is

• 20 MB for service instances on the Standard, Advanced, and Premium plans
• 2 MB for service instances on the Lite plan.