AI / ML Solutions
AI integrations, custom chatbots, NLP pipelines, and ML model development for real-world use.
Featured in 3 builds
Price on request
Quoted per project — depends on scope
Assamese-English Code-Mixed Tourism Chatbot
NLP · Deep Learning · Research
Assamese-English Code-Mixed Tourism Chatbot
A two-stage intelligent dialogue system for Assam tourism, featuring a MuRIL-based intent classifier across 44 intents with ~97% accuracy and a semantic retrieval module over 221,799 Q&A pairs covering 51 destinations - designed for low-resource code-mixed NLP.
- Year
- 2025
- Products
- 2
- Tech tags
- 6
Products in this category
The services that built Assamese-English Code-Mixed Tourism Chatbot.
Technical Solutions
Complex technical problem-solving using core CS fundamentals — algorithms, systems, automation, and more.
Featured in 2 builds
Price on request
Quoted per project — depends on scope
About this category
The case study behind the build.
Overview
A research-grade NLP dialogue system for Assam tourism that handles code-mixed Assamese-English queries — a virtually unexplored frontier in low-resource language AI. This system bridges the gap between how locals actually speak and how machines understand language.
The challenge
Code-mixed Assamese-English (mixing both languages within a single sentence) is spoken by millions but almost entirely ignored by NLP research. No existing system could handle Assam tourism queries in this natural code-mixed form across the diversity of 51 tourist destinations.
The solution
Built a two-stage pipeline: first, fine-tuned Google's MuRIL (a multilingual BERT variant pre-trained on Indian languages) for intent classification across 44 distinct tourism intent categories. Second, developed a semantic retrieval module that searches over a curated corpus of 221,799 Q&A pairs covering 51 Assam tourist destinations to return accurate, relevant answers.
Highlights
- ~97% intent classification accuracy across 44 intent categories
- 221,799 Q&A pairs curated covering 51 Assam tourist destinations
- MuRIL fine-tuned for code-mixed Assamese-English — a novel research contribution
- Two-stage architecture: intent classification feeding semantic retrieval
- Significant advancement in low-resource Indian language NLP research
