Demo: Soccer Information Retrieval via Natural Queries using SoccerRAG
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912550059245568 |
|---|---|
| author | Strand, Aleksander Theo Gautam, Sushant Midoglu, Cise Halvorsen, Pål |
| author_facet | Strand, Aleksander Theo Gautam, Sushant Midoglu, Cise Halvorsen, Pål |
| contents | The rapid evolution of digital sports media necessitates sophisticated information retrieval systems that can efficiently parse extensive multimodal datasets. This paper demonstrates 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. We present a novel interactive user interface (UI) based on the Chainlit framework which wraps around the core functionality, and enable users to interact with the SoccerRAG framework in a chatbot-like visual manner. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_01280 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Demo: Soccer Information Retrieval via Natural Queries using SoccerRAG Strand, Aleksander Theo Gautam, Sushant Midoglu, Cise Halvorsen, Pål Information Retrieval Multimedia H.3; I.2.7; H.5 The rapid evolution of digital sports media necessitates sophisticated information retrieval systems that can efficiently parse extensive multimodal datasets. This paper demonstrates 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. We present a novel interactive user interface (UI) based on the Chainlit framework which wraps around the core functionality, and enable users to interact with the SoccerRAG framework in a chatbot-like visual manner. |
| title | Demo: Soccer Information Retrieval via Natural Queries using SoccerRAG |
| topic | Information Retrieval Multimedia H.3; I.2.7; H.5 |
| url | https://arxiv.org/abs/2406.01280 |