RoRePo: Detecting the role information and relative position information for contexts in multi-turn dialogue generation

In multi-turn dialogue generation, dialogue contexts have been shown to have an important influence on the reasoning of the next round of dialogue. A multi-turn dialogue between two people should be able to give a reasonable response according to the relevant context. However, the widely used hierarchical recurrent encoder-decoder model and the latest model that detecting the relevant contexts with self-attention are facing the same problem. Their given response doesn't match the identity of the current speaker, which we call it role ambiguity. In this paper, we propose a new model, named RoRePo, to tackle this problem by detecting the role information and relative position information. Firstly, as a part of the decoder input, we add a role embedding to identity different speakers. Secondly, we incorporate self-attention mechanism with relative position representation to dialogue context understanding. Besides, the design of our model architecture considers the influence of latent variables in generating more diverse responses. Experimental results of our evaluations on the DailyDialog and DSTC7 AVSD datasets show that our proposed model advances in multi-turn dialogue generation.