A5043374188- Recommender Systems and Techniques
- Topic Modeling
- Advanced Graph Neural Networks
- Natural Language Processing Techniques
- Caching and Content Delivery
- Online Learning and Analytics
- Multimedia Communication and Technology
- Text Readability and Simplification
- Speech and dialogue systems
Shanghai Jiao Tong University
2022-2023
Goal-oriented Learning path recommendation aims to recommend learning items (concepts or exercises) step-by-step a learner promote the mastery level of her specific goals. By formulating this task as Markov decision process, reinforcement (RL) methods have demonstrated great power. Although extensive research efforts been made, previous still fail effective goal-oriented paths due under-utilizing Specifically, it is mainly reflected in two aspects: (1)The lack goal planning. When learners...
With the emergence of Large Language Models (LLMs), there has been a significant improvement in programming capabilities models, attracting growing attention from researchers. Evaluating LLMs is crucial as it reflects multifaceted abilities LLMs, and numerous downstream applications. In this paper, we propose CodeApex, bilingual benchmark dataset focusing on comprehension, code generation, correction LLMs. Programming comprehension task tests multiple-choice exam questions covering...
Utilizing large language models to generate codes has shown promising meaning in software development revolution. Despite the intelligence by general models, their specificity code generation can still be improved due syntactic gap and mismatched vocabulary existing among natural different programming languages. In addition, languages are inherently logical complex, making them hard correctly generated. Existing methods rely on multiple prompts model explore better solutions, which is...
With the prevalence of live broadcast business nowadays, a new type recommendation service, called recommendation, is widely used in many mobile e-commerce Apps. Different from classical item to automatically recommend user anchors instead items considering interactions among triple-objects (i.e., users, anchors, items) rather than binary between users and items. Existing methods based on objects, ranging early matrix factorization recently emerged deep learning, obtain objects' embeddings...
With the prevalence of live broadcast business nowadays, a new type recommendation service, called recommendation, is widely used in many mobile e-commerce Apps. Different from classical item to automatically recommend user anchors instead items considering interactions among triple-objects (i.e., users, anchors, items) rather than binary between users and items. Existing methods based on objects, ranging early matrix factorization recently emerged deep learning, obtain objects' embeddings...