Abstract
Instant messaging applications (apps) are one of the most popular methods that people use for daily communication. The usage of such apps has increased rapidly in the past couple of years. Merging Natural Language Processing (NLP) with those messaging apps has become a trending area in software application development. Localizing Chatbot conversations into different languages is an active research field. The Sinhala language is one of the most used and common languages in Sri Lanka. In our study, we introduce a novel architecture for the Sinhala language-based Chatbot development, which possesses the Natural Language Understanding (NLU) for intent identification and entity extraction. When considering the intent identification, we utilized existing tools to identify the Sinhala language-based utterances by training their machine learning-based services. The proposed architecture was tested using an in-house dataset related to the restaurant food ordering scenario. Our results show an accuracy of 89.16% for intent identification. We strongly believe that the novel conceptual architecture for the Sinhala chatbot development will provide a gateway for companies to adopt it for their customized contexts. Further, the proposed architecture will pave a way for researchers to enhance the architecture to the next level.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
