Edit model card

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

本模型的训练基于通话语音转文本数据,并在此基础上利用谷歌翻译库转换为英语文本,以完成预测与通话内容匹配的业务类型(4类)的文本分类下游任务。

其中 label 对应的业务分类如下:

0:不满

1:办理

2:咨询与查询

3:无效来话

目前模型的预测精确度约 74%, 预测错误集中在对于“无效来话”与“不满”的判断,这一定程度上是由于对这两类的判断比较复杂,而语音转文本数据损失了语气等特征,难以完全从语义从判断。另一方面,由于各标签训练样本数量不均衡,可能对预测效果造成一定程度的影响。值得一提的是,数据集中某些标注可能不太准确,这也为模型的训练带来了难度。

Downloads last month
0
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Collection including Krxk/SRP-Business-Classification-GPT2