Towards few-shot mixed-type dialogue generation  

作　　者：Zeming LIU Haifeng WANG Zeyang LEI Zheng-Yu NIU Hua WU Wanxiang CHE 

机构地区：[1]Research Center for Social Computing and Information Retrieval,Harbin 150001,China [2]Baidu Inc.,Beijing 100193,China

出　　处：《Science China(Information Sciences)》2025年第2期116-129,共14页中国科学(信息科学)(英文版)

基　　金：supported by National Key R&D Program of China(Grant No.2023YFF0725600);National Natural Science Foundation of China(Grant Nos.62236004,62206078,62441603)。

摘　　要：Building an agent capable of conducting both open-domain and task-oriented dialogues,known as mixed-type dialogues,has been an enduring challenge for the AI community.Previous approaches have focused on constructing largescale human-annotated datasets for training models.However,annotating these datasets is expensive and hinders the practical application of these models.This paper identifies a novel challenge,few-shot mixed-type dialogue generation.To address this challenge,we first present a pre-trained dialogue generation framework with modular-based architecture and prompttuning component.Additionally,we collect a mixed-type dialogue dataset that combines persona-chat with conversational recommendation or task-oriented dialogues within a single dialogue session.Specifically,the modular-based architecture allows us to easily incorporate more supervised signals and human-annotated information,thereby facilitating the learning of sessionlevel dialogue logic.We pre-train this dialogue generation framework using multiple external datasets and then fine-tune it on the mixed-type dialogue dataset we collected.Experimental results demonstrate that the three key designs—modular-based architecture,prompt-tuning component,and model pre-training—significantly enhance the performance of this framework compared to state-of-the-art baselines.

关 键 词：mixed-type dialogue dialogue generation PLATO-prompt Mixed-FS few-shot 

分 类 号：O17[理学—数学]