Search papers, labs, and topics across Lattice.
NewsTorch, a new PyTorch-based toolkit, is introduced to facilitate research and learning in news recommendation systems. It offers a modular, decoupled architecture with a GUI for dataset management and model training/evaluation. The toolkit supports standardized evaluation metrics and reproducible experiments, aiming to lower the barrier to entry for researchers and students in this domain.
Democratizing news recommendation research, NewsTorch provides a user-friendly toolkit for streamlined experimentation and learning.
News recommender systems are devised to alleviate the information overload, attracting more and more researchers'attention in recent years. The lack of a dedicated learner-oriented news recommendation toolkit hinders the advancement of research in news recommendation. We propose a PyTorch-based news recommendation toolkit called NewsTorch, developed to support learners in acquiring both conceptual understanding and practical experience. This toolkit provides a modular, decoupled, and extensible framework with a learner-friendly GUI platform that supports dataset downloading and preprocessing. It also enables training, validation, and testing of state-of-the-art neural news recommendation models with standardized evaluation metrics, ensuring fair comparison and reproducible experiments. Our open-source toolkit is released on Github: https://github.com/whonor/NewsTorch.
