The Bag-of-Words Methods with Pareto-Fronts for Similar Image Retrieval

Gabryel, Marcin

doi:10.1007/978-3-319-67642-5_31

Cited by 5 publications

(1 citation statement)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Traditional text-based classification methods have been widely applied to financial documents, relying primarily on textual features extracted from the document content. These methods include rule-based systems (Loughran and McDonald, 2011) [1], bag-of-words models (Gabryel., 2018), and machine learning techniques such as support vector machines (SVMs) (Huang et al, 2015) [3] and naive Bayes classifiers (Purda and Skillicorn, 2015) [4]. While these approaches have shown promising results in certain scenarios, they often struggle to capture the rich semantic information present in financial documents, particularly when dealing with complex, domain-specific language and terminology.…”

Section: Text-based Classification Methodsmentioning

confidence: 99%

FinEmbedDiff: A Cost-Effective Approach of Classifying Financial Documents with Vector Sampling using Multi-modal Embedding Models

2024

IRJMETS

View full text Add to dashboard Cite

Accurate classification of multi-modal financial documents, containing text, tables, charts, and images, is crucial but challenging. Traditional text-based approaches often fail to capture the complex multi-modal nature of these documents. We propose FinEmbedDiff, a cost-effective vector sampling method that leverages pre-trained multi-modal embedding models to classify financial documents. Our approach generates multi-modal embedding vectors for documents, and compares new documents with pre-computed class embeddings using vector similarity measures. Evaluated on a large dataset, FinEmbedDiff achieves competitive classification accuracy compared to state-of-the-art baselines while significantly reducing computational costs. The method exhibits strong generalization capabilities, making it a practical and scalable solution for real-world financial applications.

show abstract

Section: Text-based Classification Methodsmentioning

confidence: 99%