AI RESEARCH
Bridging the Gap Between Natural Language and Market Dynamics via High-Dimensional Representation Learning
arXiv CS.LG
•
ArXi:2605.30652v1 Announce Type: new Traditional multi-modal financial forecasting often relies on scalar sentiment scores, which fail to capture the nuances of financial news. To address this information loss, this paper explores high-dimensional representation learning by replacing discrete polarity ratings with dense FinBERT embeddings within a Transformer-based forecasting architecture. We benchmarked various embedding strategies on the FNSPID dataset, including raw embeddings, attention-weighted aggregation, and a custom Siamese network.