IRRGN: An Implicit Relational Reasoning Graph Network for Multi-turn Response Selection
This addresses the challenge of response selection in dialogue systems, offering a novel approach to enhance reasoning, though it is incremental in advancing existing methods.
The paper tackles the problem of selecting the best response in multi-turn dialogues by proposing an Implicit Relational Reasoning Graph Network, which improves reasoning ability and achieves state-of-the-art performance, surpassing human performance on the MuTual dataset.
The task of response selection in multi-turn dialogue is to find the best option from all candidates. In order to improve the reasoning ability of the model, previous studies pay more attention to using explicit algorithms to model the dependencies between utterances, which are deterministic, limited and inflexible. In addition, few studies consider differences between the options before and after reasoning. In this paper, we propose an Implicit Relational Reasoning Graph Network to address these issues, which consists of the Utterance Relational Reasoner (URR) and the Option Dual Comparator (ODC). URR aims to implicitly extract dependencies between utterances, as well as utterances and options, and make reasoning with relational graph convolutional networks. ODC focuses on perceiving the difference between the options through dual comparison, which can eliminate the interference of the noise options. Experimental results on two multi-turn dialogue reasoning benchmark datasets MuTual and MuTual+ show that our method significantly improves the baseline of four pretrained language models and achieves state-of-the-art performance. The model surpasses human performance for the first time on the MuTual dataset.