Git Product home page Git Product logo

Comments (21)

duterscmy avatar duterscmy commented on July 22, 2024

from ccks2019-ckbqa-4th-codes.

ZainZhou avatar ZainZhou commented on July 22, 2024

@MrRace 请问楼主你在运行entity_filter.py之后实体的召回率能达到多少?

from ccks2019-ckbqa-4th-codes.

MrRace avatar MrRace commented on July 22, 2024

@duterscmy 那现在上传的这个版本其实仅利用到了BERT的特征?
现在上传的这个版本features数据如下:
image
(1)这种情况,怎么写 X.append()
(2)在生成负样本时,这种随机数生成的方式为啥能够确保0.05的负样本比例?
谢谢~

from ccks2019-ckbqa-4th-codes.

ZainZhou avatar ZainZhou commented on July 22, 2024

@MrRace 我是直接使用的X.append([features[2]])

from ccks2019-ckbqa-4th-codes.

MrRace avatar MrRace commented on July 22, 2024

@MrRace 我是直接使用的X.append([features[2]])
你的feature也是类似的结构吗?

from ccks2019-ckbqa-4th-codes.

duterscmy avatar duterscmy commented on July 22, 2024

from ccks2019-ckbqa-4th-codes.

MrRace avatar MrRace commented on July 22, 2024

@duterscmy 那在SaveFilterCandiT中的new_features = features[0:2]+[features[9][0][1]] 需要改成:
new_features = features ? 还是?

from ccks2019-ckbqa-4th-codes.

MrRace avatar MrRace commented on July 22, 2024
单实体问题中,候选答案可召回的的比例为:0.730
候选答案能覆盖标准查询路径的比例为:0.461

在验证集上逻辑回归筛选后top10 召回率为0.72
单实体问题中,候选答案可召回的的比例为:0.731
候选答案能覆盖标准查询路径的比例为:0.560

@ZainZhou 你的呢?

from ccks2019-ckbqa-4th-codes.

1234560o avatar 1234560o commented on July 22, 2024

第二个逻辑回归模型只用bert特征吗,不加上之前的词频、长度、字重合度等特征吗?我理解的Bert返回的特征是一个数即正例的概率吧?

from ccks2019-ckbqa-4th-codes.

ZainZhou avatar ZainZhou commented on July 22, 2024

@MrRace 我跑的tuple_filter的比你这个低很多,因为我前面实体抽取的召回率就偏低,所以才问你entity_filter.py你可以召回多少实体

from ccks2019-ckbqa-4th-codes.

MrRace avatar MrRace commented on July 22, 2024

@MrRace 我跑的tuple_filter的比你这个低很多,因为我前面实体抽取的召回率就偏低,所以才问你entity_filter.py你可以召回多少实体
entity_filter.py上,
在验证集上逻辑回归top5筛选后,所有问题实体召回率为0.774,单实体问题实体召回率0.820
训练集的话,大概是0.8左右。

from ccks2019-ckbqa-4th-codes.

ZainZhou avatar ZainZhou commented on July 22, 2024

@MrRace 那其实差不了多少,但不知道为什么后面tuple_filter的差20个点,我再研究研究吧

from ccks2019-ckbqa-4th-codes.

duterscmy avatar duterscmy commented on July 22, 2024

from ccks2019-ckbqa-4th-codes.

MrRace avatar MrRace commented on July 22, 2024

@duterscmy 我运行tuple_filter.py的结果:

单实体问题中,候选答案可召回的的比例为:0.730
候选答案能覆盖标准查询路径的比例为:0.461
单实体问题中,候选答案可召回的的比例为:0.772
候选答案能覆盖标准查询路径的比例为:0.638

在验证集上逻辑回归筛选后top10 召回率为0.72
单实体问题中,候选答案可召回的的比例为:0.731
候选答案能覆盖标准查询路径的比例为:0.560

这个结果是偏低吗?你的大概多少?

from ccks2019-ckbqa-4th-codes.

duterscmy avatar duterscmy commented on July 22, 2024

from ccks2019-ckbqa-4th-codes.

duterscmy avatar duterscmy commented on July 22, 2024

from ccks2019-ckbqa-4th-codes.

Keerlsm avatar Keerlsm commented on July 22, 2024

 我理解错了,这是候选答案的数据啊,我今晚把流程重新跑一下告诉你

---原始邮件--- 发件人: "JaonLiu"<[email protected]> 发送时间: 2019年12月12日(周四) 上午8:57 收件人: "duterscmy/ccks2019-ckbqa-4th-codes"<[email protected]>; 抄送: "Mention"<[email protected]>;"Caomingyu"<[email protected]>; 主题: Re: [duterscmy/ccks2019-ckbqa-4th-codes] tuple_filter.py中的疑问 (#18) @duterscmy 我运行tuple_filter.py的结果: 单实体问题中,候选答案可召回的的比例为:0.730 候选答案能覆盖标准查询路径的比例为:0.461 单实体问题中,候选答案可召回的的比例为:0.772 候选答案能覆盖标准查询路径的比例为:0.638 在验证集上逻辑回归筛选后top10 召回率为0.72 单实体问题中,候选答案可召回的的比例为:0.731 候选答案能覆盖标准查询路径的比例为:0.560 这个结果是偏低吗?你的大概多少? — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or unsubscribe.


我运行tuple_filter.py的结果和上面相近,是不是参数或模型哪里有变化?我最近在做相关的工作,希望能够复现你提交的结果

from ccks2019-ckbqa-4th-codes.

counten avatar counten commented on July 22, 2024

我理解错了,这是候选答案的数据啊,我今晚把流程重新跑一下告诉你

---原始邮件--- 发件人: "JaonLiu"<[email protected]> 发送时间: 2019年12月12日(周四) 上午8:57 收件人: "duterscmy/ccks2019-ckbqa-4th-codes"<[email protected]>; 抄送: "Mention"<[email protected]>;"Caomingyu"<[email protected]>; 主题: Re: [duterscmy/ccks2019-ckbqa-4th-codes] tuple_filter.py中的疑问 (#18) @duterscmy 我运行tuple_filter.py的结果: 单实体问题中,候选答案可召回的的比例为:0.730 候选答案能覆盖标准查询路径的比例为:0.461 单实体问题中,候选答案可召回的的比例为:0.772 候选答案能覆盖标准查询路径的比例为:0.638 在验证集上逻辑回归筛选后top10 召回率为0.72 单实体问题中,候选答案可召回的的比例为:0.731 候选答案能覆盖标准查询路径的比例为:0.560 这个结果是偏低吗?你的大概多少? — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or unsubscribe.

我运行tuple_filter.py的结果和上面相近,是不是参数或模型哪里有变化?我最近在做相关的工作,希望能够复现你提交的结果

朋友,问题解决了吗,我运行的结果也差不多:还望指教

单实体问题中,候选答案可召回的的比例为:0.745
候选答案能覆盖标准查询路径的比例为:0.471
单实体问题中,候选答案可召回的的比例为:0.755
候选答案能覆盖标准查询路径的比例为:0.579

在验证集上逻辑回归筛选后top10 召回率为0.74
单实体问题中,候选答案可召回的的比例为:0.748
候选答案能覆盖标准查询路径的比例为:0.573

from ccks2019-ckbqa-4th-codes.

liupenggg avatar liupenggg commented on July 22, 2024

@duterscmy 我运行tuple_filter.py的结果:

单实体问题中,候选答案可召回的的比例为:0.730
候选答案能覆盖标准查询路径的比例为:0.461
单实体问题中,候选答案可召回的的比例为:0.772
候选答案能覆盖标准查询路径的比例为:0.638

在验证集上逻辑回归筛选后top10 召回率为0.72
单实体问题中,候选答案可召回的的比例为:0.731
候选答案能覆盖标准查询路径的比例为:0.560

这个结果是偏低吗?你的大概多少?

为啥跑出来全是0,是哪里出问题了吗?

from ccks2019-ckbqa-4th-codes.

binglinchengxiash avatar binglinchengxiash commented on July 22, 2024

@duterscmy 那在SaveFilterCandiT中的new_features = features[0:2]+[features[9][0][1]] 需要改成:
new_features = features ? 还是?

这个features应该怎么写啊?解决了吗?

from ccks2019-ckbqa-4th-codes.

JeffSuu avatar JeffSuu commented on July 22, 2024

@duterscmy 那在SaveFilterCandiT中的new_features = features[0:2]+[features[9][0][1]] 需要改成:
new_features = features ? 还是?

这个features应该怎么写啊?解决了吗?

请问这个features的问题解决了吗?写成new_features = features的效果好差。

from ccks2019-ckbqa-4th-codes.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.