TAUS DeMT™ Estimate API is a Machine Translation Quality Estimation tool, providing scores to segments outputted by a Machine Translation engine, in real-time. This enables MT users to implement condition-based workflows in their Localization processes, e.g. some content can be deemed of a quality sufficient to go live rather than requiring Post-Editing, meaning quicker turnaround time and less PE spendings. Other scenarios include benchmarking MT engines, determining which content types and/or language pairs require PE or not, and more. A detailed product sheet can be found here https://bit.ly/3GbC3l1. Contact sales@taus.net for custom solutions.
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
This listing offers one pricing dimension: Product Access (Units), which grants you access to the DeMT™ Estimate API at no cost. There are no tiers, instance sizes, or usage add-ons to choose between. You subscribe to the single free access option. The API provides automated quality estimation for machine translation, returning a quality score for each segment you submit. Because pricing is free, there is no volume-based scaling or per-character billing on this listing.
Top-of-mind questions for buyers
What does the free Product Access dimension let me do with the DeMT™ Estimate API?
Access lets you submit source text and machine-translated output to receive a quality estimation score for each segment. The API returns an objective score between 0 and 1. You define your own quality threshold to decide which segments publish and which need human review.
How is a quality estimation score calculated for each translated segment?
The API analyzes only your source text and machine-translated output. It works reference-free, meaning it needs no human-translated "gold standard" for comparison. It returns a 0 to 1 score at the segment level, flagging errors within sentences rather than across long documents.
Can I process large volumes or only real-time requests through this API?
You can submit requests in real-time mode for instant, per-segment results, or in batch mode for large asynchronous jobs. Batch processing handles millions of segments and returns results once complete. You choose the mode that fits your workflow.
www.taus.net+2
Helpful?
Vendor refund policy
This is a free product therefore no refunds are offered.
How can we make this page better?
Tell us how we can improve this page, or report an issue with this product.
Give us feedbackReport a problem with this product or seller
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA).
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.