Giter Club home page Giter Club logo

Comments (18)

red-frog avatar red-frog commented on August 23, 2024 1

https://rasa.com/docs/core/0.13.3/interactive_learning/
最新的版本使用这条命令可以解决这个问题
@Zengpr

from rasa_chatbot_cn.

GaoQ1 avatar GaoQ1 commented on August 23, 2024

please read requirements.txt, it maybe version's problem.

from rasa_chatbot_cn.

GaoQ1 avatar GaoQ1 commented on August 23, 2024

this issue give a solution.

from rasa_chatbot_cn.

Zengpr avatar Zengpr commented on August 23, 2024

我是这样安装的,版本都对的上,就是在train dialogue in online mod训练的时候有这个问题,要怎么改命令呢,不是启动server

from rasa_chatbot_cn.

gaoxing153 avatar gaoxing153 commented on August 23, 2024

Is the content of this demo changed to the medical field, or is the original rasa_chatbot code?

from rasa_chatbot_cn.

GaoQ1 avatar GaoQ1 commented on August 23, 2024

Is the content of this demo changed to the medical field, or is the original rasa_chatbot code?

demo和medical的代码有所不同,业务场景、需求和细节不同。

from rasa_chatbot_cn.

gaoxing153 avatar gaoxing153 commented on August 23, 2024

我现在在做老师的一个医疗领域的问答系统,现在遇到了一些困难,我有一些问题想向你请教一下:
1.你的医疗领域的代码是在rasa_chatbot的基础上进行修改的么?
2.你在编写代码的时候你的医疗相关的数据是存储在那里的?

from rasa_chatbot_cn.

GaoQ1 avatar GaoQ1 commented on August 23, 2024

有修改,存储数据库。

from rasa_chatbot_cn.

gaoxing153 avatar gaoxing153 commented on August 23, 2024

整个过程的工作量大么,我想用rasa做,但是现在时间不是太充足

from rasa_chatbot_cn.

GaoQ1 avatar GaoQ1 commented on August 23, 2024

工作量主要体现在你数据的处理标注,以及story的编写。这个要看你数据量的情况了。

from rasa_chatbot_cn.

gaoxing153 avatar gaoxing153 commented on August 23, 2024

目前数据库的是7万条数据,不过时间比较赶的话,我可以先只处理其中一部分数据即可,后面可以再加,故事编写的话,目前并不需要很多的对话场景,有几种就行,如果是这种情况的话工作量大概是多久?

from rasa_chatbot_cn.

Zengpr avatar Zengpr commented on August 23, 2024

能否定义实体类型字典呢,类似感冒/扁桃体发炎为disease,鸡蛋/番茄为food,直接在训练数据里加的话会不会太大了
@[disease]
~[感冒]
~[肢端肥大症]
~[血劳]
~[胃型哮喘]
~[甲状腺癌]

@[food]
~[木耳粥]
~[鸡蛋]
~[芦笋鸡丝汤]
~[桃仁]
~[桂皮]

from rasa_chatbot_cn.

GaoQ1 avatar GaoQ1 commented on August 23, 2024

@Zengpr 非常好的问题,定义实体类型字典这个我还没写component支持,是可以实现的。我们现在是在人名地名机构名这块有这个问题,所以我引入了jieba的词性标注加以支持的。
或者我在想是不是可以你给出足够多的实体在训练数据中,然后通过bert进行finetune,bert转词向量后应该会学到这块的内容。

from rasa_chatbot_cn.

zhangyanbo2007 avatar zhangyanbo2007 commented on August 23, 2024

@Zengpr 我是这样安装的,版本都对的上,就是在train dialogue in online mod训练的时候有这个问题,要怎么改命令呢,不是启动server,想知道你后来是怎么解决的。

from rasa_chatbot_cn.

zhangyanbo2007 avatar zhangyanbo2007 commented on August 23, 2024

训练的时候把这个--online --endpoints endpoints.yml 去掉
把python -m rasa_core.train --online -o models/dialogue -d mobile_domain.yml -s data/mobile_story.md --endpoints endpoints.yml
改成
python -m rasa_core.train -o models/dialogue -d mobile_domain.yml -s data/mobile_story.md
就可以了,
但是这样的话不就没有在线更新了吗?

from rasa_chatbot_cn.

zhangyanbo2007 avatar zhangyanbo2007 commented on August 23, 2024

还请楼主回答

from rasa_chatbot_cn.

GaoQ1 avatar GaoQ1 commented on August 23, 2024

这个应该是rasa-core的问题,建议去rasa-core这里看看

from rasa_chatbot_cn.

Zengpr avatar Zengpr commented on August 23, 2024

@zhangyanbo2007 这个问题我没有解决
@GaoQ1 我加入了越多实体到训练数据,bert的测试集准确率越低(甚至低于0.1),少点时达到百分之80\90。另外,实体识别始终是大问题呀,很多都是识别不了的,各种组件的都试了。
我识别的是菜名,用ner_mitie的话,字典没加的也是识别不了的呀,是不是哪里错了

from rasa_chatbot_cn.

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.