Building a Chatbot on a Closed Domain using RASA
Khang Nhut Lam, Nam Nhat Le, Jugal Kalita

TL;DR
This paper presents the development of a domain-specific chatbot for Can Tho University's College of Information and Communication Technology using RASA, employing multiple models for intent classification, entity extraction, and response improvement.
Contribution
It introduces a comprehensive approach combining SVM, CRF, LSTM, and kNN within RASA to build an effective closed-domain chatbot with a manually constructed corpus.
Findings
The chatbot responds accurately to relevant questions.
The combination of models improves entity recognition and response quality.
The system effectively handles 19 intents with high relevance.
Abstract
In this study, we build a chatbot system in a closed domain with the RASA framework, using several models such as SVM for classifying intents, CRF for extracting entities and LSTM for predicting action. To improve responses from the bot, the kNN algorithm is used to transform false entities extracted into true entities. The knowledge domain of our chatbot is about the College of Information and Communication Technology of Can Tho University, Vietnam. We manually construct a chatbot corpus with 19 intents, 441 sentence patterns of intents, 253 entities and 133 stories. Experiment results show that the bot responds well to relevant questions.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
MethodsConditional Random Field · Sigmoid Activation · Support Vector Machine · Tanh Activation · Long Short-Term Memory
