Tag
This paper compares the geometric structures induced by deep learning vector embeddings (CamemBERT) and lexical co-occurrence graph models on the French 'Great National Debate' corpus, finding similar local topology but distinct global organization, highlighting complementarity between the two approaches.
This paper evaluates traditional machine learning techniques (Random Forests, XGBoost, SVM) against a deep learning model (Unified Multi-Task Time Series Model) for customer churn prediction in retail, finding that conventional methods can outperform in predictive performance and efficiency.
This paper presents a comparative study of Graph-RAG versus standard vector-only RAG for cross-entity financial sentiment analysis, finding statistically significant improvements in entity recall and answer relevancy at modest latency cost.
This paper systematically compares the impact of model size on topic quality using seven transformer-based language models in a BERTopic pipeline, finding that model size has negligible effect on topic coherence, suggesting smaller models can perform comparably to larger ones.
This paper presents a comprehensive experimental comparison of various federated learning aggregation strategies, analyzing their performance and efficiency under both homogeneous and heterogeneous data distributions.