Intento, Inc.

🎉 We’ve published our 8th annual State of Machine Translation report. It analyzes 52 MT engines and LLMs across 11 language pairs and 9 content domains. Get your copy here ➡️ https://hubs.la/Q02zD6Z70 Here’re some key findings: 🎯 LLMs reshaped the MT landscape and now account for 55% of top-performing models 🎯 Quality varies by language and domain, with LLMs excelling in Colloquial, Education, and Entertainment 🎯 Traditional Machine Translation (MT) still outperforms in specific language pairs and domains 🎯 LLMs are less expensive but slower than MT engines 🎯 Open-source LLMs lag behind commercial offerings 🎯 Customization through translation memories, glossaries, and prompt engineering is key to eliminating errors Explore the full report to learn more about the evolving capabilities and potential of LLMs. e2f, inc.

Join us today at TAUS for a panel discussion on Questioning Quality and Evaluating LLMs. The panel will focus on building trust in automated language solutions and effective evaluation strategies for multilingual content. We’ll discuss the state of the art in automatic translation quality evaluation and what’s changing as LLMs rapidly take over the language industry. Speakers: Konstantin Savenkov (Intento), Amir Kamran (TAUS), Adam Bittlingmayer (Modelfront), Alex Yanishevsky (Smartling), Ilan Kernerman (Lexicala). Moderated by Dace Dzeguze (TAUS). #TAUS #TAUSmassivelymultilingual

Are you at AMTA today? 👀 Konstantin Savenkov, Intento’s CEO and co-founder, will present the State of Machine Translation 2024 in person. In this study, we evaluated 52 machine translation systems, including 24 LLMs, across 11 language pairs and 9 domains. Get the full report here ➡️ https://hubs.la/Q02RxyVd0. You’ll learn how LLMs are taking over the machine translation market, their strengths and weaknesses, and where older technologies still outperform the new ones. Join us to get your questions answered directly! 💥 #AMTA

We’re expanding our study on using AI to evaluate Machine Translation 🚀 This time, we’ve tested models from OpenAI, Google, Anthropic, and open-source options across three language pairs and eight domains. Our goal is to find how well various Large Language Models perform translation quality checks. We’re measuring how well they match human judgments on error types, severity, and overall quality scores. The results will help create a more efficient quality assessment process. 👉 Join us at AMTA today to learn more from Daria Sinitsyna, our Lead Computational Linguist. You’ll find out which AI models best evaluate machine translation quality across multiple languages and new tips for building a more efficient quality check system. #AMTA

We’ve increased our range of Atlassian solutions and made it easier for everyone to communicate and share knowledge in Confluence Data Center with our new Translator for Confluence. Your team needs to access content every day and when they speak multiple languages it is hard to keep up with the demand for translation. Now, with the Intento Translator for Confluence, when someone writes, searches, and reads Confluence pages or leaves comments, everything automatically translates in real-time, while keeping your terminology, style, and tone of voice. This means that everyone can access and search for content in the language they are most comfortable with, making it easier to work together. Book a demo today to learn more ➡️ https://hubs.la/Q02Rksq_0

We’ve upgraded our Translation Storage by adding the Intento LQA metric and support for TMX files. Now, you can import your approved translations into the Storage, automatically clean them using Intento LQA, and leverage them in real-time translation scenarios like website translation or document translation through the Translation Portal. Plus, you can export the clean translation memory and use it in your translation management system. This update tackles a common challenge in translation management: the gradual buildup of errors in TM that can affect translation accuracy over time. Keeping your TM accurate requires regular cleanup. This process used to take weeks or months, but now it can be done in minutes. Our update also cuts down on manual reviews, saving time and money. Book a demo to learn how to maintain high-quality TM ➡️ https://hubs.la/Q02QnQp00

Our Translation Storage saves money by reusing translations instead of starting from scratch every time. We’ve made it even better by helping you find potential translation errors. With our new Intento LQA metric, combining Multidimensional Quality Metrics and GPT-4o, you can now evaluate translation accuracy, fluency, and grammar quickly and cost-effectively. This means you can direct your linguists to focus on the content that really needs their attention, saving time and money. We’ve already tested this in our latest State of MT Report and for a study at the AMTA 2024 conference. The results show it’s much more accurate at catching critical and major translation mistakes, with fewer false alarms. Book a demo now to learn more!

#Google added 110 new languages for translation via API, with 26 of these being new to our platform, including 8 dialects. These additions are exclusive to us as they’re not available through other models on our platform. They include rare languages like Afar and Hunsrik and more common ones like Fulah and Zapotec. To better serve global communities, we’ve also added support for Betawi, Chiga, Dinka, Tulu, and many more. Our dialect offerings now include Ndau (Zimbabwe), Portuguese (Portugal), and Persian (Afghanistan). For improved accessibility, we’ve added alternative alphabets, including Berber (Latin), Bambara (N’Ko), Malay (Arabic), and Panjabi (Arabic). Whether you’re connecting with Batak Toba speakers, need Kituba translation, or require localization in Kok Borok, we have you covered. Book a demo to learn more about our comprehensive language offerings ➡️ https://hubs.la/Q02NbM7f0

10 Key Concepts you need to know when talking about AI in translation. ✅ Artificial Intelligence (AI): The broader technology that enables machines to simulate human intelligence, including tasks like translation. AI in translation involves learning and processing human language to convert text from one language to another accurately. ✅ Machine Translation (MT): The use of AI and computational linguistics to automatically translate text from one language to another without human intervention. It is the core technology behind tools like Google Translate. ✅ Neural Machine Translation (NMT): A type of machine translation that uses deep learning and neural networks to produce more natural and fluent translations. NMT models are trained on large datasets and can handle context better than traditional MT. ✅ Natural Language Processing (NLP): A branch of AI focused on the interaction between computers and human language. NLP is essential in translation as it involves understanding, interpreting, and generating human language. ✅ Corpus: A large and structured set of texts used to train machine translation systems. In AI translation, corpora (plural for corpus) are essential for teaching the machine how languages work. ✅ Domain Adaptation: The process of fine-tuning a machine translation model to perform well in specific areas (like legal, medical, or technical language) by using domain-specific data. This is crucial for high-accuracy translations in specialized fields. ✅ BLEU Score: A metric for evaluating the quality of machine-translated text by comparing it to one or more reference translations. The BLEU score helps measure how close the AI's translation is to human-level accuracy. ✅ Training Data: The vast amount of bilingual or multilingual text that is fed into an AI model to teach it how to translate. The quality and diversity of the training data significantly affect the performance of the translation system. ✅ Post-Editing: The process of reviewing and correcting machine-generated translations by human translators. Post-editing is often necessary to refine translations and ensure they meet the required quality standards. ✅ Language Pair: Refers to the two languages involved in translation, such as English to Spanish. Different language pairs can have varying levels of difficulty in machine translation, depending on linguistic differences. If you like to dive deeper into the state of the art in machine translation I recommend you to check out our partner Intento, Inc. and Konstantin Savenkov bi-annual machine translation report. You can find the latest report here: https://lnkd.in/dpRft6uw Watch out for our upcoming advanced Crowdin - Intento, Inc. course on TranslaStars Keep learning!

Awesome opportunity at Intento!