Guardado en:
| Autor principal: | |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2503.06489 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917948659073024 |
|---|---|
| author | Palahan, Sirinda |
| author_facet | Palahan, Sirinda |
| contents | Overseas investment and trade can be daunting for beginners due to the vast amount of complex information. This paper presents a chatbot system that integrates natural language processing and information retrieval techniques to simplify the document retrieval process. The proposed system identifies the most relevant content, enabling users to navigate the intricate landscape of foreign trade and investment more efficiently. Our methodology combines the BM25 model and a deep learning model to rank and retrieve documents, aiming to reduce noise in the document content and enhance the accuracy of the results. Experiments with Thai natural language queries have demonstrated the effectiveness of our system in retrieving pertinent documents. A user satisfaction survey further validated the system's effectiveness. Most respondents found the system helpful and agreed with the suggested documents, indicating its potential as a valuable tool for Thai entrepreneurs navigating foreign trade and investment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_06489 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Improving Access to Trade and Investment Information in Thailand through Intelligent Document Retrieval Palahan, Sirinda Information Retrieval Social and Information Networks Overseas investment and trade can be daunting for beginners due to the vast amount of complex information. This paper presents a chatbot system that integrates natural language processing and information retrieval techniques to simplify the document retrieval process. The proposed system identifies the most relevant content, enabling users to navigate the intricate landscape of foreign trade and investment more efficiently. Our methodology combines the BM25 model and a deep learning model to rank and retrieve documents, aiming to reduce noise in the document content and enhance the accuracy of the results. Experiments with Thai natural language queries have demonstrated the effectiveness of our system in retrieving pertinent documents. A user satisfaction survey further validated the system's effectiveness. Most respondents found the system helpful and agreed with the suggested documents, indicating its potential as a valuable tool for Thai entrepreneurs navigating foreign trade and investment. |
| title | Improving Access to Trade and Investment Information in Thailand through Intelligent Document Retrieval |
| topic | Information Retrieval Social and Information Networks |
| url | https://arxiv.org/abs/2503.06489 |