Skeleton-to-Response: Dialogue Generation Guided by Retrieval Memory

By Deng Cai, Yan Wang, Victoria Bi, Zhaopeng Tu, Xiaojiang Liu, Wai Lam, Shuming Shi. 2018

97 citations recorded by the source corpus.

Traditional generative dialogue models generate responses solely from input queries. Such information is insufficient for generating a specific response since a certain query could be answered in multiple ways. Recently, researchers have attempted to fill the information gap by exploiting information retrieval techniques. For a given query, similar dialogues are retrieved from the entire training data and considered as an additional knowledge source. While the use of retrieval may harvest extensive information, the generative models could be overwhelmed, leading to unsatisfactory performance. In this paper, we propose a new framework which exploits retrieval results via a skeleton-to-response paradigm. At first, a skeleton is extracted from the retrieved dialogues. Then, both the generated skeleton and the original query are used for response generation via a novel response generator. Experimental results show that our approach significantly improves the informativeness of the generated responses

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Retrieval-Augmented Generation, Dialogue & Conversational AI

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

1. Lawrence Carin
2. Dinghan Shen
3. Yizhe Zhang
4. Yan Wang
5. Zhiting Hu
6. Chunyuan Li
7. Shuming Shi
8. Jianfeng Gao

In Computer Vision and Pattern Recognition

1. Lawrence Carin
2. Yizhe Zhang
3. Dinghan Shen
4. Chunyuan Li
5. Olga Vechtomova
6. Yan Wang
7. Shuming Shi
8. Rada Mihalcea

In Retrieval-Augmented Generation

1. Weizhu Chen

Citations in the corpus

• What Makes Good In-Context Examples for GPT-3? (2021, background): “…2018), sentiment transfer (Li et al., 2018; Guu et al., 2018), QA (Karpukhin et al., 2020; Mao et al., 2020), dialogue generation (Yan et al., 2016; Cai et al., 2018; Song et al., 2016; Pandey et al., 2018; We-ston et al., 2018; Wu et al., 2019), text summarization (Cao et al., 2017; Peng et al.,…”
• Retrieval-Augmented Generation for AI-Generated Content: A Survey (2024, unknown): “Concretely, retrieved assets not only impose an additional velocity on particles for distribution initialization, but also help optimize the 2D diffusion model through low-rank adaptation.”
• Deep Learning for Text Style Transfer: A Survey (2020, background): “2018a; Bulté and Tezcan 2019), conversation generation (Weston, Dinan, and Miller 2018; Cai et al. 2019), code generation (Hashimoto et al.”
• Retrieval-guided Dialogue Response Generation via a Matching-to-Generation Framework (2019, methodology): “Previous studies (Weston et al., 2018; Wu et al., 2019; Cai et al., 2019) alleviated the problems by putting hard constraints on the data, which, however, greatly reduces the amount of usable data (e.”
• Benchmarking Large Language Models in Retrieval-Augmented Generation (2023, background): “2021; Trivedi et al. 2023; Li et al. 2023a), dialogue (Cai et al. 2019a,b; Peng et al. 2023), domain-specific question answering (Cui et al. 2023) and code generation (Zhou et al. 2023b).”