As machine translation (MT) continues to evolve and expand into areas such as e-commerce, global collaboration, and customer care, those interested in the future of localization are now looking to generative artificial intelligence (AI) and, in particular, large language models (LLMs) such as OpenAI’s GPT.
Unlike MT, LLMs prioritize fluency over accuracy. But while LLMs show promising results in improving the fluency of translations, they can produce hallucinations, i.e. output that is inaccurate or unrelated to the input data. With the latest release of ModernMT (V7), Translated has introduced a novel technique to increase the accuracy of neural MT models, called “Trust Attention,” which can also be used to address reliability within generative AI models.
The design and implementation of Trust Attention was inspired by how the human brain prioritizes trusted sources in the learning process, linking the origin of data to its impact on translation quality.
ModernMT V7 identifies the most valuable training data and prioritizes its learning based on that value, in a manner similar to the way humans sift through multiple sources of information to identify the most trustworthy and reliable ones. Data extracted from translations performed and reviewed by professional translators is always preferred over other data, especially unverified translation memory content acquired from web crawling, which is typically used by most MT systems today.
According to an evaluation by professional translators, Trust Attention alone improves MT quality by up to 42%, and by an average of 16.5% in cases across the top 50 languages. It is interesting to note that in many high-resource languages, such as Italian and Spanish, it showed significant improvements (in the 30% range) in human evaluations.
ModernMT V7 New Features: Up to 60% Better MT Quality
ModernMT V7 is the evolution of Translated’s renowned adaptive MT system, recognized as a leader in Machine Translation Software Vendor Assessment by IDC Marketscape 2022 and as “the most advanced implementation of responsive MT” in CSA Research’s 2023 Vendor Briefing.
In addition to Trust Attention, ModernMT V7 includes several new features that further enhance the reliability and dependability of MT output. Here are the most impactful:
- Advanced Terminology Control: Along with its ability to learn the client’s terminology from past translations, ModernMT now provides companies with self-managed glossary control to ensure brand and context-specific terminology consistency.
- DataClean AI: V7 relies on a new sanitization algorithm that identifies and removes poor-quality data to refine the training material and reduce the likelihood of hallucinations.
- Expanded Context: ModernMT can now leverage up to 100,000 words of document content —Four times more than GPT-4— to preserve style and terminology preferences, providing unparalleled document-specific accuracy in MT suggestions and solving problems such as gender bias and inconsistent terminology.
- Profanity Filter: V7 masks words in translation suggestions that could be regarded as inappropriate in the target language, minimizing the possibility of cultural offenses.
The combined effect of all the improvements and innovations described above has a significant impact on the overall performance and capabilities of ModernMT. The MT quality is now considered to be 45 to 60% better than the previous version according to human evaluations.
These improvements have already greatly reduced the Time to Edit (TTE) for MT suggestions. At the end of July, TTE showed a 20% reduction, reaching a record low of 1.74 seconds. This milestone indicates an acceleration towards singularity in translation, a trend further supported by preliminary TTE data collected continuously since the 1.74 seconds record was established.
The Hallmark of the Symbiosis Between Translators and MT
ModernMT V7 is available in 200 languages and covers all the fastest-growing economies likely to emerge over the next 20 years. Its hallmark is the ability of the MT model to learn from corrections in real-time, enabling a powerful symbiosis between the sensitivity of professional translators and the speed and capacity of MT. Thanks to this unique approach, combined with Translated’s vast community of professional translators and leading AI-enabled localization solutions (Gartner 2022), Airbnb was able to ditch the translate button and become one of the top 3 global brands (Global by Design 2023).
Success stories like that of Airbnb and others, along with market research, have led Translated to estimate that once MT reaches what is commonly referred to as “parity with human translation” (singularity in translation), we can expect a 100-fold increase in MT requests alongside a 10-fold growth in demand for professional translations.
We are entering a new era in which significantly larger volumes of content will be translated automatically. In this scenario, professional translators play an increasingly important role, not only in guiding the MT through the adaptive process but also in ensuring that the key messages are appropriately conveyed. By engaging the best translators with the best adaptive MT, companies can now take on projects that simply weren’t feasible before.
Towards LLMs for Translation
Recently, Translated conducted a large-scale study to compare the performance of the most advanced MT systems with LLMs in terms of enterprise readiness. The findings showed real potential for LLMs, particularly in terms of translation quality, and also revealed areas where improvements are needed. Based on this research, Translated believes elements of both MT systems and LLMs will be critical as we move forward, and plans to provide in-depth insights into the use of LLMs in translation in the coming weeks and months.
At Translated, we’re passionate about tackling challenges that others consider out of reach. We’re constantly innovating MT to improve this powerful symbiosis between human creativity and artificial intelligence that will help us fulfill our mission: to allow everyone to understand and be understood in their own language.
ModernMT is available with a one-month free trial at modernmt.com.
For translators looking for seamless integration, ModernMT is accessible directly from within Matecat, Translated’s AI-powered, web-based CAT tool. Plug-ins are also available for Trados and MemoQ.