RAP-Net: Recurrent Attention Pooling Networks for Dialogue Response Selection
This addresses the problem of selecting appropriate responses in real-world dialogue systems, with incremental improvements for the domain.
The paper tackles response selection in dialogue modeling by introducing RAP-Net, a framework that estimates relevance between dialogue contexts and candidates, achieving effectiveness and generalization across datasets in DSTC7 experiments.
The response selection has been an emerging research topic due to the growing interest in dialogue modeling, where the goal of the task is to select an appropriate response for continuing dialogues. To further push the end-to-end dialogue model toward real-world scenarios, the seventh Dialog System Technology Challenge (DSTC7) proposed a challenging track based on real chatlog datasets. The competition focuses on dialogue modeling with several advanced characteristics: (1) natural language diversity, (2) capability of precisely selecting a proper response from a large set of candidates or the scenario without any correct answer, and (3) knowledge grounding. This paper introduces recurrent attention pooling networks (RAP-Net), a novel framework for response selection, which can well estimate the relevance between the dialogue contexts and the candidates. The proposed RAP-Net is shown to be effective and can be generalized across different datasets and settings in the DSTC7 experiments.