Focused domain contextual AI chatbot framework for resource poor languages

Abstract

In today's business world, providing reliable customer service is equally important as delivering better products for maintaining a sustainable business model. As providing customer service requires human resource and money, businesses are often shifting towards artificial intelligence system for necessary customer interaction. However, these traditional chatbot architectures depend heavily on natural language processing (NLP), it is not feasible to implement for the languages with little to no prior NLP backbone. In this work, we propose a semi-supervised artificially intelligent chatbot framework that can automate parts of primary interaction and customer service. The primary focus of this work is to build a chatbot which can generate contextualized responses in any language without depending much on rich NLP background and a vast number of a prior data set. This system is designed in such a way that with a dictionary of a language and regular customer interaction dataset, it can provide customer services for any business in any language. This architecture has been used to build a customer service bot for an electric shop, and different analysis has been done to evaluate the performance of individual components of the framework to show its competence to provide reliable response generation in comparison with other approaches. ARTICLE HISTORY

AI business model: an integrative business approach

“…If businesses and companies start a new venture, these will be expected to a derivative of endeavors to revolutionize from place to place bequest big business or possibly more expected heritage classifications. Businesses are progressively observing for workforces who can modernize and who have a ground-breaking approach because they diagnose the requirement for teams who see foremost hitches, view them as openings, and devise ground-breaking elucidations (Muthusamy, Slominski, & Ishakian, 2018;Paul, Haque Latif, Amin Adnan, & Rahman, 2019).…”

AI Business Model: An Integrative Business Approach

“…If businesses and companies start new venture, these will be expected to derivative of endeavors to revolutionize from place to place bequest big business or possibly more expected, heritage classi cations. Businesses are progressively observing for workforces who can modernize and who have ground-breaking approach because they diagnose the requirement for teams who see foremost hitches, view them as openings and device ground-breaking elucidations (Muthusamy et al, 2018, Paul et al, 2019.…”

Large-scale Translation to Enable Response Selection in Low Resource Languages: A COVID-19 Chatbot Experiment

“…To increase the quality and quantity of training samples, the authors also proposed a Dialogue Augmentation method to provide enough conversations for training, randomly extracting coherent parts of the dialogues and combining them into positive and negative conversations of different time intervals. [Paul et al 2019] attempts to provide easy implementation of a multilingual context-aware chatbot for any domain. The dataset was built using two different languages -Bangla and English.…”

“…Bangla represents an example of a resourcepoor language. [Paul et al 2019] divides the response selection to a given query into two steps: pre-processing and text classification. Pre-processing is needed to avoid variation of the exact words being considered different; this step recurs to stemming processing.…”

“…Pre-processing is needed to avoid variation of the exact words being considered different; this step recurs to stemming processing. [Paul et al 2019] uses the Kolkata Bangla Academy Dictionary for Bangla Language to perform N-Gram stemming, which is a statistical approach and is entirely language independent because it only uses a word list to find the stem. In the text classification step, the authors investigated different algorithms to find the best possible relationship between a new query and an already existing dataset.…”