Madhubala Sundaram


Fixing paper assignments

  1. Please select all papers that belong to the same person.
  2. Indicate below which author they should be assigned to.
Provide a valid ORCID iD here. This will be used to match future papers to this author.
Provide the name of the school or the university where the author has received or will receive their highest degree (e.g., Ph.D. institution for researchers, or current affiliation for students). This will be used to form the new author page ID, if needed.

TODO: "submit" and "cancel" buttons here


2024

pdf bib
LangBot-Language Learning Chatbot
Madhubala Sundaram | Pattabhi RK Rao | Sobha Lalitha Devi
Proceedings of the 21st International Conference on Natural Language Processing (ICON)

Chatbots are being widely used in educational domain to revolutionize how students interact and learn along with traditional methods of learning. This paper presents our work on LangBot, a chatbot developed for learning Tamil language. LangBot developed integrates the interactive features of chatbots with the study material of the Tamil courses offered by Tamil Virtual Academy, Government of Tamil Nadu. LangBot helps students in enhancing their learning skills and increases their interest in learning the language. Using semi-automatic methods, we generate question and answers related to all topics in the courses. We then develop a generative language model and also Retrieval Augmented Generation (RAG) so that the system can incorporate new syllabus changes. We have performed manual user studies. The results obtained are encouraging. This approach offers learners an interactive tool that aligns with their syllabus. It is observed that this enriches the overall learning experience.