New Machine Translation University chapter on selecting MT systems, new languages available through MT Hub, and a handful of AI news that made April so remarkable ✨
April unveiled 🌸:
- New chapter 📖: Selecting MT systems based on available assets
- New languages from Microsoft and ModernMT
- PDF translations (with OCR!) now available via Intento Portal
- Glossary labels — New!
- Intento Translator for Chrome — Updated!
- RoyalFlush Translate—New!
- Dolly 2.0 by Databricks
- HuggingChat by Hugging Face
- Building LLM apps for production
- Eventful April
New Machine Translation University chapter 📖: Selecting MT systems based on available assets
Where do you start when choosing MT systems? 🤔 Check out the latest addition to our Machine Translation University covering:
🌍 Language support
💰 Pricing
📚 Glossary availability
🧠 TM size
🎯 Domain adaptation
🔒 Compliance & security
Dive in and remember — in MT, cost and quality don’t always correlate 🤷🏻♀
New languages from Microsoft and ModernMT
Microsoft Translator recently added Konkani, Maithili, and Sindhi from India 🇮🇳, Sinhala from Sri Lanka 🇱🇰, and Lower Sorbian from Germany 🇩🇪 — all ready for use via Intento MT Hub!
And ModernMT now boasts 200 languages, with 29 new for our platform.
Our live demo is a great place to try how different vendors stack up for other language pairs 👉🏻 https://inten.to/api-platform/ai/text/translate.
PDF and OCR translations now available via Intento Portal
Intento MT Portal now supports the translation of PDF files. It even supports scanned PDFs using the embedded OCR feature. The MT Portal is available to customers who have a subscription to MT Hub for Employee Experience.
Glossary labels — new feature alert 🔔
You can now add labels to your glossaries for easier navigation. Did you know Intento Glossaries work in a provider-agnostic fashion and can be case-sensitive? More on that here.
Eventful April
In late April, Pavel Doronin (our Product Director) presented on XTM Live how we augment MT with Automatic Post-Editing to apply glossaries, and control tone of voice, gender, and other aspects of translations. Of course, GPT is involved!
At the same conference, Andy Nikulin (Customer Success Director) shared our case study on gendered translations at scale, discussing how Intento tried out GPT for adjusting gender and tone of voice in video translations (case study coming soon!)
Earlier, at the end of March, we sat down with Edith from NetApp and Theresa from Nike to talk about what lies beyond MT (recording available) and how to navigate today’s increasingly AI-driven localization landscape.
Finally, at the GALA conference in Dublin, IKEA shared their first successful experiments with GPT-based Automatic Post-Editing — a 25% edit distance reduction on top of their custom NMT.
RoyalFlush Translate
A new addition to our lineup of MT providers, RoyalFlush Translate excels in seamless global financial communication. Drawing on extensive financial data and comprehensive knowledge, it provides high-quality translations for text, documents, speech, and images in 10+ languages, including Malay, Vietnamese, and Indonesian.
Dolly 2.0 by Databricks
In mid-April, DataBricks released Dolly 2.0 — an open-source, instruction-tuned 12B-parameter LLM based on the EleutherAI’s Pythia-6.9b model and fine-tuned on a high-quality human-generated dataset.
Dolly 2.0 is available for commercial use without any API fees or third-party risks. Is this the perfect moment you’ve been waiting to try LLMs? 💡
HuggingChat by Hugging Face
Hugging Face, an ML tools developer and AI code hub, launches its own open-source challenger to ChatGPT. Hugging Face now serves only as a UI for the Open Assistant model but aims to grow into a chatbot client supporting many other models — so be sure to keep an eye on it! 🤗
Building LLM apps for production
What does it take to make your cool LLM app production-ready? ❓In her recent piece, Chip Huyen talks about the ambiguity of natural languages, the stochastic nature of LLMs, and rapid evolution, then examines complex use cases involving tasks, agents, and control flows.
News from the front lines of AI and MT
- Companies Are Starting to Launch GPT-4-Powered Machine Translation Services
- Machine Translation Used for Cuneiform Tablets
- Computer science research team explores how machine learning can translate sign language
- Scientists Use GPT AI to Passively Read People’s Thoughts in Breakthrough
- OpenAI’s CEO confirms the company isn’t training GPT-5 and ‘won’t for some time’
- How Do We Ensure an A.I. Future That Allows for Human Thriving?
- Comparing Bing Chat, Bard Chat and ChatGPT (Video)
