A multilingual semantic search chatbot framework
| Dublin Core | PKP Metadata Items | Metadata for this Document | |
| 1. | Title | Title of document | A multilingual semantic search chatbot framework |
| 2. | Creator | Author's name, affiliation, country | Vinay R; RV College Of Engineering; India |
| 2. | Creator | Author's name, affiliation, country | Thejas B U; RV College Of Engineering; India |
| 2. | Creator | Author's name, affiliation, country | H A Vibhav Sharma; RV College Of Engineering; India |
| 2. | Creator | Author's name, affiliation, country | Poonam Ghuli; RV College Of Engineering; India |
| 2. | Creator | Author's name, affiliation, country | Shobha G; RV College Of Engineering; India |
| 3. | Subject | Discipline(s) | Natural Language Processing; General AI Applications; |
| 3. | Subject | Keyword(s) | Bidirectional encoder representations from transformers; Chatbot; Cross-lingual question answering dataset; Natural language processing; Stanford question answering dataset; Universal sentence encoder |
| 4. | Description | Abstract | Chatbots are conversational agents which interact with users and simulate a human interaction. Companies use chatbots on their customer-facing sites to enhance user experience by answering questions about their products and directing users to relevant pages on the site. Existing chatbots which are used for this purpose give responses based on pre-defined frequently asked questions (FAQs) only. This paper proposes a framework for a chatbot which combines two approaches-retrieval from a knowledge base consisting of question answer pairs, combined with a natural language search mechanism which can scan through the paragraphs of text information. A feedback-based knowledge base update is implemented which provides continuous improvement in user experience. The framework achieves a result of 81.73 percent answer matching on stanford question answering dataset (SQuAD) 1.1 and 69.21 percent answer matching on SQuAD 2.0. The framework also performs well on languages such as Spanish (67.32 percent answer match), Russian (61.43 percent answer match), and Arabic (51.63 percent answer match). By means of zero shot learning. |
| 5. | Publisher | Organizing agency, location | Institute of Advanced Engineering and Science |
| 6. | Contributor | Sponsor(s) | R V College Of Engineering |
| 7. | Date | (YYYY-MM-DD) | 2024-06-01 |
| 8. | Type | Status & genre | Peer-reviewed Article |
| 8. | Type | Type | |
| 9. | Format | File format | |
| 10. | Identifier | Uniform Resource Identifier | https://ijai.iaescore.com/index.php/IJAI/article/view/23765 |
| 10. | Identifier | Digital Object Identifier (DOI) | http://doi.org/10.11591/ijai.v13.i2.pp2333-2341 |
| 11. | Source | Title; vol., no. (year) | IAES International Journal of Artificial Intelligence (IJ-AI); Vol 13, No 2: June 2024 |
| 12. | Language | English=en | en |
| 14. | Coverage | Geo-spatial location, chronological period, research sample (gender, age, etc.) | |
| 15. | Rights | Copyright and permissions |
Copyright (c) 2024 Institute of Advanced Engineering and Science This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. |