BriefGPT.xyz
Jul, 2022
多模式对话理解与生成的场景感知提示
Scene-Aware Prompt for Multi-modal Dialogue Understanding and Generation
HTML
PDF
Bin Li, Yixuan Weng, Ziyu Ma, Bin Sun, Shutao Li
TL;DR
本文介绍了LingJing团队在NLPCC-2022-Shared-Task-4多模态对话理解和生成中实验的方案,通过提出情景感知提示和多任务策略来联合建模情景和对话生成的多模态理解,在场景了解和对话生成方面实现了最先进的性能。
Abstract
This paper introduces the schemes of Team LingJing's experiments in
nlpcc-2022-shared-task-4
multi-modal dialogue
Understanding and Generation (MDUG). The MDUG task can be divided into two phases: multi-modal con
→