How to create and evaluate a translation application.
application_variant_id
in the top right:
TRANSLATION
and follow the formatting instructions. Supported file types include CSV
, XSLX
, JSON
and JSONL
.
TRANSLATION
as the Dataset Type and pick a dataset that matches that schema. If the dataset has multiple version, you will have to select the version of the dataset for which you want to upload the outputs. Ensure to follow the upload instructions for the file type you are choosing. We support the same file types as for the evaluation dataset upload, CSV
, XSLX
, JSON
and JSONL
.
Contributor
evlauations and no auto-evaluation from the UI.
TranslationTestCaseSchema
function is a helper function that allows you to quickly create a Translation Evaluation through the flexible evaluations framework. This function assumes the application you want to evaluate has an orgin text and language as an input and the expected translation of the document as the expected input. It takes in inputs origin_text
, language
, and expected_translation
and creates a test case object.
In order to use this function, you start by creating a list of data for your test cases. The test case data is represented as an object that contains a origin_text
(a string containing the text you want translated), language
(the translation language), and expected_translation
(a string containing the expected translation).
TranslationTestCaseSchema
function.