Retrieval-guided Dialogue Response Generation via a Matching-to-Generation Framework

By Deng Cai, Yan Wang, Wei Bi, Zhaopeng Tu, Xiaojiang Liu, Shuming Shi. 2019

90 citations recorded by the source corpus.

End-to-end sequence generation is a popular technique for developing open domain dialogue systems, though they suffer from the safe response problem. Researchers have attempted to tackle this problem by incorporating generative models with the returns of retrieval systems. Recently, a skeleton-then-response framework has been shown promising results for this task. Nevertheless, how to precisely extract a skeleton and how to effectively train a retrieval-guided response generator are still challenging. This paper presents a novel framework in which the skeleton extraction is made by an interpretable matching model and the following skeleton-guided response generation is accomplished by a separately trained generator. Extensive experiments demonstrate the effectiveness of our model designs.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Augmenting Transformers with KNN-Based Composite Memory for Dialog (2020, methodology): “Further work has explored hybrid models, for example using the output of a retrieval model as input for a generative model (Dinan et al., 2018; Weston et al., 2018; Cai et al., 2019; Zhu et al., 2020).”
Automatic Document Sketching: Generating Drafts from Analogous Texts (2021, background): “Cai et al. (2019) induce an intermediate template for response generation explicitly, but from a single retrieved relevant response.”
Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning (2021, background): “…models, fuzzy match score (Gu et al., 2018; Zhang et al., 2018; Hayati et al., 2018; Xu et al., 2020), attention mechanisms (Cao et al., 2018; Cai et al., 2019), and dot products between sentence representations (Lewis et al., 2020; Xu et al., 2020) are usual scoring functions to re-rank the…”