Curriculum Recommendations Using Transformer Base Model with InfoNCE Loss And Language Switching Method
Xiaonan Xu, Bin Yuan, Yongyao Mo, Tianbo Song, Shulin Li
TL;DR
This paper addresses learning equality in curriculum recommendations, noting challenges from content conflicts and translation noise. It proposes a Transformer-based encoding with InfoNCE loss for precise topic-content matching and a language-switching strategy to mitigate translation ambiguities. Key contributions include a Transformer Base Model with limited sequence length, symmetric InfoNCE loss focusing on diagonal similarities, and a language-switching data augmentation approach evaluated on Kolibri Studio data, achieving a top cross-validation score of $0.66314$. The results suggest robust multilingual content alignment, supporting equitable, personalized curriculum recommendations in diverse linguistic contexts.
Abstract
The Curriculum Recommendations paradigm is dedicated to fostering learning equality within the ever-evolving realms of educational technology and curriculum development. In acknowledging the inherent obstacles posed by existing methodologies, such as content conflicts and disruptions from language translation, this paradigm aims to confront and overcome these challenges. Notably, it addresses content conflicts and disruptions introduced by language translation, hindrances that can impede the creation of an all-encompassing and personalized learning experience. The paradigm's objective is to cultivate an educational environment that not only embraces diversity but also customizes learning experiences to suit the distinct needs of each learner. To overcome these challenges, our approach builds upon notable contributions in curriculum development and personalized learning, introducing three key innovations. These include the integration of Transformer Base Model to enhance computational efficiency, the implementation of InfoNCE Loss for accurate content-topic matching, and the adoption of a language switching strategy to alleviate translation-related ambiguities. Together, these innovations aim to collectively tackle inherent challenges and contribute to forging a more equitable and effective learning journey for a diverse range of learners. Competitive cross-validation scores underscore the efficacy of sentence-transformers/LaBSE, achieving 0.66314, showcasing our methodology's effectiveness in diverse linguistic nuances for content alignment prediction. Index Terms-Curriculum Recommendation, Transformer model with InfoNCE Loss, Language Switching.