A Scalable Chatbot Platform Leveraging Online Community Posts: A Proof-of-Concept Study
This addresses the data scarcity problem for chatbot developers, but it is incremental as it builds on existing methods with a new data source.
The paper tackled the difficulty of obtaining large-scale conversational data by proposing a pipeline to use processed online community posts as pseudo-conversational data, demonstrating that chatbots built this way can yield proper responses.
The development of natural language processing algorithms and the explosive growth of conversational data are encouraging researches on the human-computer conversation. Still, getting qualified conversational data on a large scale is difficult and expensive. In this paper, we verify the feasibility of constructing a data-driven chatbot with processed online community posts by using them as pseudo-conversational data. We argue that chatbots for various purposes can be built extensively through the pipeline exploiting the common structure of community posts. Our experiment demonstrates that chatbots created along the pipeline can yield the proper responses.