NLP Solution for Language Acquisition

Alphary’s business challenge

An educational startup from Austria named Alphary set an ambitious goal to redefine the English language learning experience and accelerate language acquisition by automatically providing learners with feedback and increasing user engagement with a gamification strategy. To do this, they needed to introduce innovative AI algorithms and completely redesign the user journey. The most challenging task was to determine the best educational approaches and translate them into an engaging user experience through NLP solutions that are easily accessible on the go for learners’ convenience.

Alphary had already collaborated with Oxford University to adopt experience of teachers on how to deliver learning materials to meet the needs of language learners and accelerate the second language acquisition process. They recognized the critical need to develop a mobile app applying NLP in language learning that would automatically provide feedback to learners and adapt the learning process to their pace, encouraging learners to go further in their journeys toward a new language.

To redefine the experience of how language learners acquire English vocabulary, Alphary started looking for a technology partner with artificial intelligence software development expertise that also offered UI/UX design services.

Intellias came up with a strategic framework for collaborating with the Alphary product team on all design and development processes, from gathering requirements and creating user personas to releasing several NLP applications in education to the DACH market and adapting them to new Arabic-speaking markets.

NLP solution for language acquisition delivered

Together with our client’s team, Intellias engineers with deep expertise in the eLearning and EdTech industry started developing an NLP learning app built on the best scientific approaches to language acquisition, such as the world recognized Leitner flashcard methodology. The most critical part from the technological point of view was to integrate AI algorithms for automated feedback that would accelerate the process of language acquisition and increase user engagement. We decided to implement Natural Language Processing (NLP) algorithms that use corpus statistics, semantic analysis, information extraction, and machine learning models for this purpose.

After completing an AI-based backend for the NLP foreign language learning solution, Intellias engineers developed mobile applications for iOS and Android. Our designers then created further iterations and new rebranded versions of the NLP apps as well as a web platform for access from PCs.

While developing and implementing AI components and NLP algorithms adapted to the eLearning and education industry, the Intellias team focused on:

• A server-side component that performs NLP analysis of users’ answers in a fill-in-the-gap exercise based on collocation extraction, word space modules, and the Link Grammar parser
• An AI component for automatically generating fill-in-the-gap exercises and creating answer options given a certain headword and semantic context
• A sense disambiguation and keyword extraction algorithm
• Semantic similarity algorithms for words, texts, and sentences
• Robust statistics and analytics of learners’ progress and typical mistakes to improve the learning process

Our client also needed to introduce a gamification strategy and a mascot for better engagement and recognition of the Alphary brand among competitors. This was a big part of the AI language learning app that Alphary entrusted to our designers. The Intellias UI/UX design team conducted deep research of user personas and the journey that learners take to acquire a new language.

Intellias designers introduced Feebu, a Feedback Butterfly, as a visible representation of the AI assistant that provides fast feedback on four main criteria: grammar, spelling, meaning, and natural sound. This virtual AI learning assistant can adapt to a learner’s pace and fill in gaps that appear during communication with additional exercises to improve any of these four criteria.

Users get instant feedback on the words they enter. Tapping on the wings brings up detailed information about what’s incorrect about an answer. After getting feedback, users can try answering again or skip a word during the given practice session. On the Finish practice screen, users get overall feedback on practice sessions, knowledge and experience points earned, and the level they’ve achieved.

Intellias engineers and designers worked together closely to implement and embody all NLP for language learning functionality into a virtual assistant that allows users to quickly acquire English vocabulary and guides them through the language acquisition process while suggesting several gamification scenarios with friends, family members, colleagues, or any other app users. Since the first release of Alphary’s NLP app, our designers have been continuously updating the interface design based using our mobile development services, aligning it with fresh market trends and integrating new functionality added by our engineers.

After releasing the first version of the NLP mobile app for the DACH market, our client entrusted Intellias designers to adapt the application’s UI to a range of Alphary’s end customers, including famous German and British educational publishers who purchased the app’s functionality and required their own branding.

Intellias engineers and designers provided our client with:

• All drafts, sketches, and prototypes for a desirable, feasible, and viable custom language eLearning solution
• A prototype and full-fledged AI-driven system that evaluates student texts and voices
• Intelligent Android, iOS, and web applications with an AI backend
• A parsed and redesigned multilingual dictionary with various types of exercises
• Tech consulting and continuous quality assurance to cover all types of manual and automated testing

Business outcome

Alphary has an impressive success story thanks to building an AI- and NLP-driven application for accelerated second language acquisition models and processes. Oxford University Press, the biggest publishing house in the world, has purchased their technology for global distribution. The Intellias team has designed and developed new NLP solutions with unique branded interfaces based on the AI techniques used in Alphary’s native application. The success of the Alphary app on the DACH market motivated our client to expand their reach globally and tap into Arabic-speaking countries, which have shown a tremendous demand for AI-based and NLP language learning apps.

Intellias helped Alphary:

• Get recognized by the world’s most renowned publishing houses: Oxford, Cambridge, and Macmillan
• Set up a UI/UX process for adapting and redesigning NLP solutions for end customers
• Conduct in-depth user research, resulting in defined user personas, pains, and motivations
• Develop and integrate a server-side AI component that analyzes student answers using NLP technologies
• Become one of the most popular language learning mobile apps in the DACH region for its engaging gamification strategy
• Gain a huge audience measured in the hundreds of thousands of satisfied English learners
• Expand their business to Arabic and Turkish markets thanks to multilingual support