Abstract

Conversational Artificial Intelligence (AI) has undergone substantial progress, evolving from rule-based systems to advanced transformer-driven multilingual models. However, research for low-resource Indian languages—particularly Marathi and Hindi—remains limited despite rapid technological advances. This review synthesizes studies from 2000 to 2025, covering rule-based chatbots, retrieval methods, Seq2Seq architectures, multilingual transformers, and self-supervised speech models such as wav2vec 2.0 and HuBERT. The analysis highlights key linguistic challenges, including agglutination, free word order, transliteration, regional accents, and pervasive code-mixing. Although models like mBERT, XLM-R, and MuRIL significantly improve multilingual understanding, they still struggle with hybrid inputs and domain-specific conversational tasks. Persistent gaps include limited datasets, weak ASR–NLU integration, and insufficient cultural grounding. The review outlines future directions for developing robust, culturally aligned Marathi–Hindi–English chatbots.

References

• Abbet, Christian, et al. “Churn Intent Detection in Multilingual Chatbot Conversations and Social Media.” Proceedings of the 22nd Conference on Computational Natural Language Learning (CoNLL 2018), Association for Computational Linguistics, 2018, pp.161–170.
• Adamopoulou, Eleni, and Lefteris Moussiades. “Chatbots: History, Technology, and Applications.” Machine Learning with Applications, vol. 2, 2020, article 100006.
• Baevski, Alexei, et al. “wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations.” Advances in Neural Information Processing Systems, vol. 33, 2020, pp. 12449–12460.
• Bali, Kalika, et al. “Code-Mixing: The New Normal in India.” Proceedings of the 11th International Conference on Natural Language Processing (ICON 2014), 2014.
• Brown, Tom B., et al. “Language Models Are Few-Shot Learners.” Advances in Neural Information Processing Systems, vol. 33, 2020, pp. 1877–1901.
• Caldarini, Guendalina, Sardar Jaf, and Kenneth McGarry. “A Literature Survey of Recent Advances in Chatbots.” Information, vol. 13, no. 1, 2022, article 41.
• Cassell, Justine, et al. “Embodied Conversational Agents: Representation and Intelligence in User Interfaces.” AI Magazine, vol. 22, no. 4, 2000, pp. 67–83.
• Chakravarthi, Bharathi Raja, et al. “DravidianCodeMix: Sentiment Analysis and Offensive Language Identification Dataset for Dravidian Languages in Code-Mixed Text.” Language Resources and Evaluation, vol. 57, 2023, pp. 367–403.
• Conneau, Alexis, et al. “Unsupervised Cross-Lingual Representation Learning at Scale.” Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL 2020), 2020, pp. 8440–8451.
• Conneau, Alexis, et al. “XLS-R: Self-Supervised Cross-Lingual Speech Representation Learning at Scale.” Proceedings of Interspeech 2021, 2021, pp. 2278–2282.
• Deriu, Jan, et al. “Survey on Evaluation Methods for Dialogue Systems.” Artificial Intelligence Review, vol. 54, 2021, pp. 755–810.
• Devlin, Jacob, et al. “BERT: Pre-Training of Deep Bidirectional Transformers for Language Understanding.” Proceedings of NAACL-HLT 2019, 2019, pp. 4171–4186.
• Fryer, Luke K., and R. Carpenter. “Bots as Language Learning Tools.” Computer Assisted Language Learning, vol. 19, no. 4–5, 2006, pp. 465–477.
• Gambäck, Björn, and Amitava Das. “On Measuring the Complexity of Code-Mixing.” Proceedings of the 11th International Conference on Natural Language Processing (ICON 2014), 1st Workshop on Language Technologies for Indian Social Media, 2014, pp. 1–7.
• Guerreiro, Miguel Porfirio, et al. “Conversational Agents for Health and Well-Being Across the Life Course: Systematic Review.” JMIR Medical Informatics, vol. 9, no. 9, 2021, e26680.
• Hsu, Wei-Ning, et al. “HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units.” IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 29, 2021, pp. 3451–3460.
• Khanuja, Simran, et al. “MuRIL: Multilingual Representations for Indian Languages.” arXiv preprint arXiv:2103.10730, 2021.
• Kuhail, Mohammad Amin, et al. “Interacting with Educational Chatbots: A Systematic Review.” Education and Information Technologies, vol. 28, 2023, pp. 973–1018.
• Kunchukuttan, Anoop, et al. “IndicNLPSuite: Monolingual Corpora, Evaluation Benchmarks and Pre-Trained Multilingual Language Models for Indian Languages.” Findings of the Association for Computational Linguistics: EMNLP 2020, 2020, pp. 4948–4961.
• Labadze, Levan, et al. “Role of AI Chatbots in Education: Systematic Literature Review.” International Journal of Educational Technology in Higher Education, vol. 20, no. 1, 2023, article 32.
• Laranjo, Liliana, et al. “Conversational Agents in Healthcare: A Systematic Review.” Journal of the American Medical Informatics Association, vol. 25, no. 9, 2018, pp. 1248–1258.
• Li, Jiwei, et al. “A Diversity-Promoting Objective Function for Neural Conversation Models.” Proceedings of NAACL-HLT 2016, 2016, pp. 110–119.
• Montenegro, Jorge Luis Z., et al. “Survey of Conversational Agents in Health.” Expert Systems with Applications, vol. 129, 2019, pp. 56–67.
• Okonkwo, Chinedu Wilfred, and Adenike Ade-Ibijola. “Chatbots Applications in Education: A Systematic Review.” Computers and Education: Artificial Intelligence, vol. 2, 2021, article 100033.
• Park, Min Sook, et al. “A Survey of Conversational Agents and Their Applications for Self-Management of Chronic Conditions.” Proceedings of the IEEE 47th Annual Computers, Software, and Applications Conference (COMPSAC 2023), 2023, pp. 1064–1075.
• Philip, Jithin, et al. “Revisiting Low Resource Status of Indian Languages in Machine Translation.” arXiv preprint arXiv:2008.04860, 2020.
• Radford, Alec, et al. “Language Models Are Unsupervised Multitask Learners.” OpenAI Technical Report, 2019.
• Serban, Iulian Vlad, et al. “Building End-to-End Dialogue Systems Using Generative Hierarchical Neural Network Models.” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 30, 2016.
• Shang, Lifeng, Zhengdong Lu, and Hang Li. “Neural Responding Machine for Short-Text Conversation.” Proceedings of ACL-IJCNLP 2015, 2015, pp. 1577–1586.
• Singh, Sonali Uttam, and Akbar Siami Namin. “A Survey on Chatbots and Large Language Models: Testing and Evaluation Techniques.” Natural Language Processing Journal, vol. 10, 2025, article 100128.
• Sitaram, Sunayana, et al. “A Survey of Code-Mixed Speech and Natural Language Processing.” ACM Computing Surveys, vol. 55, no. 2, 2023, pp. 1–38.
• Smutný, Petr, and Petra Schreiberová. “Chatbots for Learning: A Review of Educational Chatbots for the Facebook Messenger.” Computers & Education, vol. 151, 2020, article 103862.
• Sutskever, Ilya, Oriol Vinyals, and Quoc V. Le. “Sequence to Sequence Learning with Neural Networks.” Advances in Neural Information Processing Systems, vol. 27, 2014, pp. 3104–3112.
• Thara, S., and K. Poornachandran. “Code-Mixing: A Brief Survey.” Proceedings of the 2nd International Conference on Recent Trends in Advanced Computing (ICRTAC), 2019.
• Tudor Car, Lorainne, et al. “Conversational Agents in Health Care: Scoping Review and Conceptual Analysis.” Journal of Medical Internet Research, vol. 22, no. 8, 2020, e17158.
• Vaswani, Ashish, et al. “Attention Is All You Need.” Advances in Neural Information Processing Systems, vol. 30, 2017, pp. 5998–6008.
• Verma, Tanya, et al. “ASR for Low Resource and Multilingual Noisy Code-Mixed Speech.” Proceedings of Interspeech 2023, 2023, pp. 4269–4273.
• Vinyals, Oriol, and Quoc V. Le. “A Neural Conversational Model.” Proceedings of the 32nd International Conference on Machine Learning, Deep Learning Workshop, 2015.
• Wallace, Richard S. “The Anatomy of A.L.I.C.E.” Parsing the Turing Test: Philosophical and Methodological Issues in the Quest for the Thinking Computer, edited by Robert Epstein et al., Springer, 2009, pp. 181–210.
• Zhou, Li, et al. “The Design and Implementation of XiaoIce, an Empathetic Social Chatbot.” Computational Linguistics, vol. 46, no. 1, 2020, pp. 53–93.
• Kunchukuttan, Anoop, et al. “IndicNLPSuite: Monolingual Corpora, Evaluation Benchmarks and Pre-Trained Multilingual Language Models for Indian Languages.” Findings of the Association for Computational Linguistics: EMNLP 2020, 2020, pp. 4948–4961.
• Chakravarthi, Bharathi Raja, et al. “DravidianCodeMix: Sentiment Analysis and Offensive Language Identification Dataset for Dravidian Languages in Code-Mixed Text.” Language Resources and Evaluation, vol. 57, 2023, pp. 367–403.
• Gambäck, Björn, and Amitava Das. “On Measuring the Complexity of Code-Mixing.” Proceedings of the 11th International Conference on Natural Language Processing (ICON 2014), 2014, pp. 1–7.
• Conneau, Alexis, et al. “Unsupervised Cross-Lingual Representation Learning at Scale.” Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL 2020), 2020, pp. 8440–8451.
• Khanuja, Simran, et al. “MuRIL: Multilingual Representations for Indian Languages.” arXiv preprint arXiv:2103.10730, 2021.
• Devlin, Jacob, et al. “BERT: Pre-Training of Deep Bidirectional Transformers for Language Understanding.” Proceedings of NAACL-HLT 2019, 2019, pp. 4171–4186.
• Sitaram, Sunayana, et al. “A Survey of Code-Mixed Speech and Natural Language Processing.” ACM Computing Surveys, vol. 55, no. 2, 2023, pp. 1–38.
• Bali, Kalika, et al. “Code-Mixing: The New Normal in India.” Proceedings of the 11th International Conference on Natural Language Processing (ICON 2014), 2014.
• Kunchukuttan, Anoop, et al. “IndicNLP Suite: Monolingual Corpora, Evaluation Benchmarks and Pre-Trained Models for Indian Languages.” Findings of EMNLP 2020, 2020, pp. 4948–4961.
• Baevski, Alexei, et al. “wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations.” Advances in Neural Information Processing Systems, vol. 33, 2020, pp. 12449–12460.
• Hsu, Wei-Ning, et al. “HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units.” IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 29, 2021, pp. 3451–3460.
• Conneau, Alexis, et al. “XLS-R: Self-Supervised Cross-Lingual Speech Representation Learning at Scale.” Proceedings of Interspeech 2021, 2021, pp. 2278–2282.
• Sutskever, Ilya, et al. “Sequence to Sequence Learning with Neural Networks.” Advances in Neural Information Processing Systems, vol. 27, 2014, pp. 3104–3112.