Follow Me: Conversation Planning for Target-driven Recommendation Dialogue Systems

Jian Wang, Dongding Lin, Wenjie Li
8/6/2022
cs.CL

No official code found. Best implementation: iwangjian/Plan4RecDial (12 stars, Apache-2.0, last commit 2023-08-01).

Abstract

Recommendation dialogue systems aim to build social bonds with users and provide high-quality recommendations. This paper pushes forward towards a promising paradigm called target-driven recommendation dialogue systems, which is highly desired yet under-explored. We focus on how to naturally lead users to accept the designated targets gradually through conversations. To this end, we propose a Target-driven Conversation Planning (TCP) framework to plan a sequence of dialogue actions and topics, driving the system to transit between different conversation stages proactively. We then apply our TCP with planned content to guide dialogue generation. Experimental results show that our conversation planning significantly improves the performance of target-driven recommendation dialogue systems.

View on arXivView PDF

Code Implementations(1)

iwangjian/Plan4RecDialCommunity100%
Apache-2.0

Follow Me: Conversation Planning for Target-driven Recommendation Dialogue Systems

121Shell, PythonOct 14, 20213 years agoApache-2.0
dialogue-generationplanningtarget-driven-dialogue

Similar Papers

STEP: Stepwise Curriculum Learning for Context-Knowledge Fusion in Conversational Recommendation

86% match1 repo12025

Improving Conversational Recommendation Systems via Counterfactual Data Simulation

85% match1 repo152023

CoRE-CoG: Conversational Recommendation of Entities using Constrained Generation

85% match2023

Large Language Model Driven Recommendation

84% match2024

Target-oriented Proactive Dialogue Systems with Personalization: Problem Formulation and Dataset Curation

83% match1 repo312023

Knowledge-Enhanced Conversational Recommendation via Transformer-based Sequential Modelling

83% match2024

Cite this paper

@article{wang2022follow,
  title  = {Follow Me: Conversation Planning for Target-driven Recommendation Dialogue Systems},
  author = {Jian Wang and Dongding Lin and Wenjie Li},
  year   = {2022},
  eprint = {2208.03516},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2208.03516v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2208.03516.svg)](https://codeofpaper.com/paper/2208.03516)

Discussion