-
Notifications
You must be signed in to change notification settings - Fork 2
CBMI 2024
-
SoccerRAG: Multimodal Soccer Information Retrieval via Natural Queries
-
Demo: Soccer Information Retrieval via Natural Queries using SoccerRAG
The rapid evolution of digital sports media necessitates sophisticated information retrieval systems that can efficiently parse extensive multimodal datasets. This paper introduces SoccerRAG, an innovative framework designed to harness the power of Retrieval Augmented Generation (RAG) and Large Language Models (LLMs) to extract soccer-related information through natural language queries.
By leveraging a multimodal dataset, SoccerRAG supports dynamic querying and automatic data validation, enhancing user interaction and accessibility to sports archives. Evaluations indicate that SoccerRAG effectively handles complex queries, offering significant improvements over traditional retrieval systems in terms of accuracy and user engagement.
The results underscore the potential of using RAG and LLMs in sports analytics, paving the way for future advancements in the accessibility and real-time processing of sports data.
- Utilizes Retrieval Augmented Generation (RAG) and Large Language Models (LLMs)
- Supports natural language queries for soccer information retrieval
- Validates the user's input before query the database
- Leverages multimodal dataset including video, audio, and text
- Enhances user interaction and accessibility to sports archives
- Demonstrates improved accuracy and user engagement compared to traditional systems
- Efficient parsing of extensive multimodal sports datasets
- Enhanced accessibility to sports archives
- Real-time processing of sports data
- Advanced sports analytics and insights
SoccerRAG represents a significant step forward in sports information retrieval, combining cutting-edge AI technologies to create a more intuitive and powerful way to interact with soccer data.