高技术通讯2025，Vol.35Issue(11)：1163-1173,11.DOI:10.3772/j.issn.1002-0470.2025.11.002
生成式对话的差异感知对比学习方法
Difference-aware contrastive learning for dialogue generation
摘要
Abstract
Contrastive learning has been widely used as an effective fine-tuning method.However,data augmentation techniques in this context still face some challenges.Due to the discrete nature of natural language,traditional data augmentation methods can cause significant semantic changes;additionally,models may become overly sensitive to surface features while neglecting critical semantic differences.To mitigate these obstacles,this work proposes a difference-aware contrastive learning method.This method uses equivalent contrast enhancement to allow the model to be insensitive to semantically equivalent augmented data,while employing a non-equivalent difference discrimi-nator to capture semantic changes in the augmented samples,thereby keeping the model sensitive to potential non-equivalent augmented data.This work conducts experiments on two open-domain dialogue datasets,and the results show that models fine-tuned using the proposed method achieve significant improvements in both quantitative evalu-ations and human assessments compared to baseline models using previous fine-tuning approaches.Additionally,this work conducts ablation studies,which validate the effectiveness of the different modules in the proposed method.关键词
自然语言处理/开放域对话系统/对比学习/差异感知方法/预训练模型Key words
natural language processing/open-domain dialogue system/contrastive learning/difference-aware method/pre-trained model引用本文复制引用
WANG Chengrui,CHEN Hongshen,CAI Hengyi,LI Tianhao,XU Sulong,ZHAO Xiaofang..生成式对话的差异感知对比学习方法[J].高技术通讯,2025,35(11):1163-1173,11.基金项目
国家重点研发计划(2023YFC3303804)资助项目. （2023YFC3303804）
