Multilingual Indian COVID-19 Chatbot

被引:0
作者
Thara, S. [1 ]
Jyothiratnam [2 ]
Sonpole, Satya Harthik [1 ]
Inturi, Bhargav [1 ]
Krishna, Ajay [1 ]
Vuppala, Sahit [1 ]
Nedungadi, Prema [1 ]
机构
[1] Amrita Vishwa Vidyapeetham, Dept Comp Sci & Engn, Amrita Sch Comp, Amritapuri, India
[2] Amrita Vishwa Vidyapeetham, Amrita CREATE, Amrita Sch Comp, Amritapuri, India
来源
SMART TRENDS IN COMPUTING AND COMMUNICATIONS, VOL 2, SMARTCOM 2024 | 2024年 / 946卷
关键词
BERT; BM25; Chatbot; COVID-19; GloVe embeddings; Healthcare; Multilingual; Natural language processing; Squad; SIF; TF-IDF;
D O I
10.1007/978-981-97-1323-3_5
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Albeit the COVID-19 era has ended, common people are ravaged by lingering misconceptions about the pre- and post-COVID effects. Chatbot is a computer program that simulates human conversation. Chatbots communicate with users via text or voice using natural language. This paper presents the development of a MILIC-19 chatbot to augur user-friendly interfaces for Indians, where there are many official languages. We have integrated the Google Translate API, allowing our chatbot to converse in 19 Indian languages. The MILIC-19 chatbot application responds to user queries by matching them with the keywords in the database to retrieve an appropriate response from the database. Handling Question-Answer tasks is configured in two layers, each serving a unique purpose in providing the best results. The first layer is an information retrieval model that leverages the power of Term Frequency-Inverse Document Frequency and Smooth Inverse Frequency to calculate inverted indices and Best Match to retrieve the top 15 articles related to the query. The second layer is a Bio-BERT model trained on the Stanford QA dataset. This combination of techniques enables the model to effectively provide relevant information by prioritizing the most important documents based on the frequency of the terms in the query.
引用
收藏
页码:47 / 64
页数:18
相关论文
共 50 条
[31]   Potential of Selected Indian Herbs for COVID-19 [J].
Verma, Ravindra ;
Misra, Vaibhav ;
Tiwari, Dileep ;
Bisen, Prakash S. .
CURRENT TRADITIONAL MEDICINE, 2021, 7 (04) :566-573
[32]   Effects of COVID-19 on Indian Energy Consumption [J].
Aruga, Kentaka ;
Islam, Md Monirul ;
Jannat, Arifa .
SUSTAINABILITY, 2020, 12 (14)
[33]   Impact of COVID-19 on convergence in Indian districts [J].
Chakrabarty, Manisha ;
Mukherjee, Subhankar .
INDIAN GROWTH AND DEVELOPMENT REVIEW, 2022, 15 (2/3) :198-209
[34]   THE BARRIERS ANALYSIS OF SUPPLY CHAIN MANAGEMENT DURING COVID-19 PANDEMIC IN INDIAN INDUSTRIES: COVID-19 PANDEMIC IN INDIAN INDUSTRIES [J].
Gupta, Srikant .
INDEPENDENT JOURNAL OF MANAGEMENT & PRODUCTION, 2022, 13 (01) :127-141
[35]   COVID-19 Lockdown in India: An Experimental Study on Promoting Mental Wellness Using a Chatbot during the Coronavirus [J].
Raji, V. P. Harshini ;
Maheswari, P. Uma .
INTERNATIONAL JOURNAL OF MENTAL HEALTH PROMOTION, 2022, 24 (02) :189-205
[36]   SIAAA-C: A student interactive assistant android application with chatbot during COVID-19 pandemic [J].
Sweidan, Saadeh Z. ;
Abu Laban, Sarah S. ;
Alnaimat, Njood A. ;
Darabkh, Khalid A. .
COMPUTER APPLICATIONS IN ENGINEERING EDUCATION, 2021, 29 (06) :1718-1742
[37]   Balancing Healthcare and Economy Amidst the COVID-19 Pandemic: An Indian Experience [J].
Dhar, Ruby ;
Jee, Babban ;
Karmakar, Subhradip .
RISK MANAGEMENT AND HEALTHCARE POLICY, 2021, 14 :827-833
[38]   Bilingual Chatbot For Covid-19 Detection Based on Symptoms Using Rasa NLU [J].
Mellah, Youssef ;
Bouchentouf, Toumi ;
Rahmoun, Noureddine ;
Rahmoun, Mohammed .
2022 2ND INTERNATIONAL CONFERENCE ON INNOVATIVE RESEARCH IN APPLIED SCIENCE, ENGINEERING AND TECHNOLOGY (IRASET'2022), 2022, :553-557
[39]   Integrating Chatbot and Augmented Reality Technology into Biology Learning during COVID-19 [J].
Chuang, Chi-Hung ;
Lo, Jung-Hua ;
Wu, Yan-Kai .
ELECTRONICS, 2023, 12 (01)
[40]   Politics of Language in COVID-19: Multilingual Perspectives from South Africa [J].
Rudwick, Stephanie ;
Sijadu, Zameka ;
Turner, Irina .
POLITIKON, 2021, 48 (02) :242-259