Document Library

sdl machine translation cloud error

Claudia Heredia — Wed, 17 Apr 2024 22:22:01 GMT

hi there, why am i getting this error? I have the freelance version of trados 2019. I am running the plug in for MT. I am not starting a cloud project but i get this annoying message. Help please. thank you.

HTML codes of an .ods file

Ilaria Lupone — Sun, 13 Aug 2023 18:40:11 GMT

Hi,

I have just uploaded an .ods file containing HTML code in Trados. The HTML code is not recognized as tag/placeable. The text has also been pretranslated.

How can I set the HTML codes as tag so that it is better visualized?

Thank you very much for your help!

SDL Machine Translation Quality Report: Q4 2019 through Q1 2020

Jane Hendricks (former member) — Wed, 19 Feb 2020 21:52:55 GMT

This report provides a summary of how market-leading MT software solutions perform on two popular automated metrics (BLEU and LEPOR) that attempt to measure relative MT quality. These metrics provide a rough guide to the automatic translation quality users can expect from these products. Keep in mind that this is a single measure of a single dimension of product performance and fit. Buyers and evaluators of MT should consider their overall requirements and business objectives when evaluating any technology, including machine translation.

The basic ideas behind Neural Nets are 30 years old. What is new is the ability to deploy them with big data and computing power.

Kirti Vashee — Thu, 11 Apr 2019 16:31:55 GMT

When you boil it down, AI today is deep learning, and deep learning is backprop—which is amazing, considering that backprop is more than 30 years old. Once you understand the story of backprop, you’ll start to understand the current moment in AI, and in particular the fact that maybe we’re not actually at the beginning of a revolution. Maybe we’re at the end of one.

Neural nets are just thoughtless fuzzy pattern recognizers, and as useful as fuzzy pattern recognizers can be—hence the rush to integrate them into just about every kind of software—they represent, at best, a limited brand of intelligence, one that is easily fooled.

Great overview and discussion on BLEU Scores

Kirti Vashee — Wed, 20 Mar 2019 18:28:38 GMT

This is a technical overview of BLEU done in a systematic step-by-step manner and a great way to understand what it can do and what it cannot do well. It also points to how it may or may not work in other areas of NLP beyond MT

Great discussion on the evolution of Neural MT at the algorithmic level - technical but clear

Kirti Vashee — Thu, 14 Mar 2019 22:24:55 GMT

Best Practices for Enterprise Scale Post-Editing

Sharon Luongo — Fri, 11 Nov 2016 15:29:58 GMT