关于GCU、沐曦GPGPU、MLU、0卡V100资源4月7日恢复上架的公告>>> 关于共建具身智能开源数据集的倡议>>> 关于云脑任务中统一路径访问方式的公告>>> 关于将启智集群GPU资源迁移至智算集群的公告>>>
1030514181
/
OpenAttack
Not watched
1
2
Fork 0
Code
Releases 0 Wiki Activity
Issues 4 Pull Requests 0 Datasets Model Cloudbrain
Issues
/
Detail
Labels Milestones
New Issue

#10 计算BLEU指标用于评估攻击效果

Closed
created 1 year ago by 1030514181 · 2 comments
1030514181 self-assigned this 1 year ago
1030514181 commented 1 year ago
Owner

Bleu是IBM在2002提出的，用于机器翻译任务的评价，发表在ACL，引用次数10000+，原文题目是“BLEU: a Method for Automatic Evaluation of Machine Translation”。

它的总体思想就是准确率，假如给定标准译文reference，神经网络生成的句子是candidate，句子长度为n，candidate中有m个单词出现在reference，m/n就是bleu的1-gram的计算公式。

BLEU还有许多变种。根据n-gram可以划分成多种评价指标，常见的指标有BLEU-1、BLEU-2、BLEU-3、BLEU-4四种，其中n-gram指的是连续的单词个数为n。

BLEU-1衡量的是单词级别的准确性，更高阶的bleu可以衡量句子的流畅性。

Bleu是IBM在2002提出的，用于机器翻译任务的评价，发表在ACL，引用次数10000+，原文题目是“BLEU: a Method for Automatic Evaluation of Machine Translation”。 它的总体思想就是准确率，假如给定标准译文reference，神经网络生成的句子是candidate，句子长度为n，candidate中有m个单词出现在reference，m/n就是bleu的1-gram的计算公式。 BLEU还有许多变种。根据n-gram可以划分成多种评价指标，常见的指标有BLEU-1、BLEU-2、BLEU-3、BLEU-4四种，其中n-gram指的是连续的单词个数为n。 BLEU-1衡量的是单词级别的准确性，更高阶的bleu可以衡量句子的流畅性。
1030514181 commented 1 year ago
Owner

计算公式如下：
image

计算公式如下： ![image](/attachments/249d50eb-2ea0-4043-843a-39f2813ecd58)
image.png
22 KiB
1030514181 started working 1 year ago
1030514181 closed this issue 1 year ago
1030514181 stopped working 1 year ago
4s
Sign in to join this conversation.
No Branch/Tag Specified
Clear branch or tag
Branches Tags
Labels
Apply labels
Clear labels
No items
No Label
Milestone
Set milestone
Clear milestone
No items
No Milestone
Assignees
Assign users
Clear assignees
No Assignees
 1030514181
1 Participants
Notifications
Total Time Spent: 4s
Due Date

No due date set.

Dependencies

This issue currently doesn't have any dependencies.

Write Preview
Loading…
Cancel
Save
There is no content yet.
Delete Branch '%!s(MISSING)'

Deleting a branch is permanent. It CANNOT be undone. Continue?

No
Yes
Please read the following content carefully:

Dear OpenI User

Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.

For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》

Agree and continue
Disagree, exit