End-to-End Trainable Chatbot for Restaurant Recommendations

Abstract: Task-oriented chatbots can be used to automate a specific task, such as finding a restaurant and making a reservation. Implementing such a conversational system can be difficult, requiring domain knowledge and handcrafted rules. The focus of this thesis was to evaluate the possibility of using a neural network-based model to create an end-to-end trainable chatbot that can automate a restaurant reservation service. For this purpose, a sequence-to-sequence model was implemented and trained on dialog data. The strengths and limitations of the system were evaluated and the prediction accuracy of the system was compared against several baselines. With our relatively simple model, we were able to achieve results comparable to the most advanced baseline model. The evaluation has shown some promising strengths of the system but also significant flaws that cannot be overlooked. The current model cannot be used as a standalone system to successfully conduct full conversations with the goal of making a restaurant reservation. The review has, however, contributed with a thorough examination of the current system, and shown where future work ought to be focused.