Memory-based deep neural attention (mDNA) for cognitive multi-turn response retrieval in task-oriented chatbots

One of the important criteria used in judging the performance of a chatbot is the ability to provide meaningful and informative responses that correspond with the context of a user's utterance. Nowadays, the number of enterprises adopting and relying on task-oriented chatbots for profit is increasing. Dialog errors and inappropriate response to user queries by chatbots can result in huge cost implications. To achieve high performance, recent AI chatbot models are increasingly adopting the Transformer positional encoding and the attention-based architecture. While the transformer performs optimally in sequential generative chatbot models, recent studies has pointed out the occurrence of logical inconsistency and fuzzy error problems when the Transformer technique is adopted in retrieval-based chatbot models. Our investigation discovers that the encountered errors are caused by information losses. Therefore, in this paper, we address this problem by augmenting the Transformer-based retrieval chatbot architecture with a memory-based deep neural attention (mDNA) model by using an approach similar to late data fusion. The mDNA is a simple encoder-decoder neural architecture that comprises of bidirectional long short-term memory (Bi-LSTM), attention mechanism, and a memory for information retention in the encoder. In our experiments, we trained the model extensively on a large Ubuntu dialog corpus, and the results from recall evaluation scores show that the mDNA augmentation approach slightly outperforms selected state-of-the-art retrieval chatbot models. The results from the mDNA augmentation approach are quite impressive.