Posts

Deepseek for Translation 2: a Robin Hood Moment in AI

Part 1 of the evaluation with scores Full-sized infographic Сommunity’s evaluation of Deepseek’s translation accuracy is complete. Conclusion: Deepseek is a top-notch translation powerhouse racing nose-to-nose with the market leaders. The differences were small, and the ratings depended more on personal preferences of evaluators towards computer-generated translation, rather than model performance. And it will get […]

Deepseek for Translation: a Flash Evaluation

On January 28 we called for language industry peers to evaluate the new large language model Deepseek for translation tasks. More than 30 volunteers came forward, and the first results have already come in. We’re hoping to have at least 10-15 language combinations evaluated within the scope of this expercise. We will publish information as […]

Quality Estimation Draws Nearer to Adoption

Machine Translation Quality Estimation (QE) is a method to triage good and bad machine translations with the goal of reducing translation costs. In October, a translation company claimed they recently achieved savings of 35% in a $1 million localization contract. This is one of the first public proofs of the economic benefits of QE, and […]

Guide: How to Fine-Tune GPT-4o for Translation

OpenAI has recently expanded its offerings by making GPT-4o available for fine-tuning! Just in time for us to explore the custom translation opportunities provided by this advanced solution on the market. This new capability allows users to tailor GPT-4o to meet specific localization requirements, ensuring that the translation output adheres to pre-defined terminologies, translation memories, […]

Guide: How to Fine-Tune GPT-3.5 for Translation

OpenAI platform offers its users an opportunity to fine-tune GPT-3.5. For localization needs, one can train the AI to generate translation output with specific terminology, translation memory, and style guides. After the training, the model will not be able to generate dialogue-like answers anymore and will become a tool only for translation. When you train […]

Shopware 6 Connector

Custom.MT has developed a translation plugin for Shopware 6, a Germany-based eCommerce platform. The plugin connects online stores with machine translation and GenAI workflows in our Console. Expanding European shops for cross-border trade is complex, and this application provides support for nuanced and high-quality automated translation for various product categories. A medium-sized online store has […]

Mix Machine Translation + GenAI

Custom.MT Console has rolled out a key update: a way to combine the output of popular machine translation engines with generative AI. Localization specialists may now easily style MT output and “mix and blend colors” to get a more accurate and evocative machine translation that speaks with the audience. Machine translation engines are reliable but […]

Measuring Language Quality with Gen AI

This article details tactics to detect and label translation errors with GPT-4 AI model and to build bots for language quality assurance. In the example of error labeling above, Rembrandt’s name is misspelled. That’s a Fluency error – not something critical impeding our understanding, but looking sloppy on a marketing piece that refers to a […]

Google Adaptive Translation in Custom.MT Console

Machine translation based on large language models (LLMs) has come to CAT tools and TMS. We’re announcing the TMS integration with Google Adaptive Translation, which leverages Google’s LLMs to produce more fluent and natural-sounding translations. Through Custom.MT Console, Google Adaptive Translation is now available in Trados, memoQ, and Smartling. Google Adaptive Translation is a product […]

Designing AI Translation Performance Dashboards

Localization teams in 2024 had a renewed interest in implementing AI translation in workflows. It was a reasonable way to trim their budgets and improve per-word costs. However, just like today, monetization often became a struggle because the mechanism to track human post-editing effort – unlike that of an AI – fairly and responsively is […]

GPT-4 Turbo and Vision in Localization

On Monday, November the 6th, OpenAI upveiled the new improved models. Let’s explore the main features of GPT-4 Turbo and its possible implementations in the localization field. The release is a gauntlet of challenge to a broad range of AI companies. Not just LLM builders like Antropic and Cohere, but also speech recognition, synthetic voice, […]

Reflecting on the Golden Jubilee Locworld 50: A Rollercoaster of Localization Trends

The Golden Jubilee Locworld 50 conference recently concluded, leaving attendees with a whirlwind of thoughts and emotions. As the conference ended, attendees struggled to distil key takeaways from this milestone event, evident in puzzled expressions. Conversations were peppered with puzzled expressions, furrowed brows, and hesitant responses. “Errr…” “Hmmm…” “(Shrug) Yeah.” After some contemplation, two recurring […]

Posts

Categories

Webinars