In this paper, we proposed a transfer learning-based English language learning chatbot, whose output generated by GPT-2 can be explained by corresponding ontology graph rooted by finetuning dataset. We design three levels for systematically English learning, including phonetics level for speech recognition and pronunciation correction, semantic level for specific domain conversation, and the simulation of "free-style conversation" in English-the highest level of language chatbot communication as 'free-style conversation agent'. For academic contribution, we implement the ontology graph to explain the performance of free-style conversation, following the concept of XAI (Explainable Artificial Intelligence) to visualize the connections of neural network in bionics, and explain the output sentence from language model. From implementation perspective, our Language Learning agent integrated the mini-program in WeChat as front-end, and fine-tuned GPT-2 model of transfer learning as back-end to interpret the responses by ontology graph.
Chatbot operates task-oriented customer services in special and open domains at different mobile devices. Its related products such as knowledge base Question-Answer System also benefit daily activities. Chatbot functions generally include automatic speech recognition (ASR), natural language understanding (NLU), dialogue management (DM), natural language generation (NLG) and speech synthesis (SS). In this paper, we proposed a Transfer-based English Language learning chatbot with three learning system levels for real-world application, which integrate recognition service from Google and GPT-2 Open AI with dialogue tasks in NLU and NLG at a WeChat mini-program. From operational perspective, three levels for learning languages systematically were devised: phonetics, semantic and "free-style conversation" simulation in English. First level is to correct pronunciation in voice recognition and learning sentence syntactic. Second is a converse special-domain and the highest third level is a language chatbot communication as freestyle conversation agent. From implementation perspective, the Language Learning agent integrates into a WeChat mini-program to devise three user interface levels and to finetune transfer learning as back-end language model to generate responses for users. With the combination of the two parts about operation and implementation, based on the Neural Network model of transfer learning technology, different users test the system with open-domain topic acquiring good communication experience and proved it ready to be the industrial application to be used.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.