Back To Projects

A new style of teaching: Exploring the benefits of visual language learning

Yuna S.

This project was designed to investigate the efficiency and likelihood of people learning a new language through means of an AI that would help translate objects in day to day life to a language that the user would want to learn.


This project was designed to investigate the efficiency and likelihood of people learning a new language through means of an AI that would help translate objects in day to day life to a language that the user would want to learn. This specific project would help to benefit a better understanding of languages and enable the user to have better connection and communication skills with others. The overall approach taken to achieve this goal came in the form of two parts: object detection and natural language processing (NLP). The first part contained training the AI on certain categories of objects which would then be put through the second part of the AI, the translation. The user would also be able to interact with the AI by inputting their own data and selecting a certain language they would like to learn. The AI was seen to have around a 35% accuracy rate in determining the correct image but had a few errors when encountering the translation side of things. Regardless, some important conclusions were that the AI was successful in being able to translate languages and would certainly help people in their language learning endeavors.

Explore More!

Yuna S.
Shreya Parchure
MD-PhD student at UPenn

Related Projects

Detecting Facial Expressions

This paper shows that machine learning algorithms can be used in order to classify emotions into different categories. The most promising results were from the K-nearest neighbor model, with 61.5% accuracy in the training set, and 32.1% accuracy in the testing set.
Bertran M.
Mentored by Odysseas Drosis
Optimizing Student Success Predictions using Artificial Intelligence

This work investigates using AI and neural networks to enhance predictions of student success and optimize resource allocation in education, finding that advanced models can significantly improve support for students and address resource imbalances.
Sameeksha V.
Mentored by Jose Reyes
Predicting Dropouts Using Machine Learning Models

High dropout rates in high schools and universities have become a major complication in many countries following the upsurge of the Covid 19 pandemic. With the accuracy provided, this model should be held in high regard as it serves as an efficient method for predicting possible college dropouts in university.
Viksar D.
Mentored by Eric Bradford