An End-to-End Goal-Oriented Dialog System with a Generative Natural Language Response Generation
This work addresses incremental improvements for goal-oriented dialog systems, enhancing their applicability in real-life scenarios.
The paper tackled limitations in end-to-end goal-oriented dialog systems by incorporating positional encodings to model word order and using a feedforward neural network for word-by-word response generation, achieving better accuracies in Dialog bAbI Tasks and saving computation time and space consumption.
Recently advancements in deep learning allowed the development of end-to-end trained goal-oriented dialog systems. Although these systems already achieve good performance, some simplifications limit their usage in real-life scenarios. In this work, we address two of these limitations: ignoring positional information and a fixed number of possible response candidates. We propose to use positional encodings in the input to model the word order of the user utterances. Furthermore, by using a feedforward neural network, we are able to generate the output word by word and are no longer restricted to a fixed number of possible response candidates. Using the positional encoding, we were able to achieve better accuracies in the Dialog bAbI Tasks and using the feedforward neural network for generating the response, we were able to save computation time and space consumption.