Skip to content

检索模块语料库和检索性能的问题 #9

Description

@Mercurialzs

您好,我正在尝试复现retrieval模块,我目前构建检索语料库的思路是把训练集中全部对话的语句都放到语料库中,检索模型使用的是all-mpnet-base-v2,检索目标是去除与query相同句子之后的top1,不过top1的emotion标签与query的emotion标签匹配准确率只有40-50%,所以想请问下构建语料库和检索方法是否有什么问题?论文中实现的top1检索语句emotion标签与query匹配准确率大约是多少?

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions