Rasa是一套對話機(jī)器人的開源框架，主要用于構(gòu)建面向任務(wù)（Task Oriented）的對話系統(tǒng)。
NLU自然語言理解
-
基于規(guī)則
-
神經(jīng)網(wǎng)絡(luò)方法
DIET(Dual Intent Entity Transformer)
在Rasa中兩種方法都可以使用，但神經(jīng)網(wǎng)絡(luò)方法是核心
一個(gè)rasa項(xiàng)目包含的文件：
-
domain
包含了聊天機(jī)器人需要知道的所有東西
- Responses: these are the things the assistant can say to users
- Intents: These are categories of things users say
- Slots: These are variables remembered over the course of a conversation
- Entities: these are pieces of information extracted from incoming text
- Forms and Actions: These add application logic and extend what your assistant can do
-
Stories
training data to teach your assistant what is should do next
-
Rules
a way to describe short pieces of conversations that always go the same way
-
config
- language 指定機(jī)器人使用的語言
- pipeline 定義用于檢測意圖和實(shí)體的步驟
- policies 指定如何響應(yīng)用戶輸入的對話管理技術(shù)
Do
- Use actual user conversations as stories
- Have small stories that aren’t full conversations
- Use rules for one-off interactions(checking account balance, checking if this is a bot)
Don’t文章來源：http://www.zghlxwxcb.cn/news/detail-480299.html
- Use rules for multi-turn interactions
- Use OR statements and checkpointing often
- Write out every possible conversation flow start to finish
- Delay user testing
Rasa style CDD:文章來源地址http://www.zghlxwxcb.cn/news/detail-480299.html
- You only need to start with the most popular, important intents & a way to handle things outside them
- Continue to build from there if that’s what users need
到了這里，關(guān)于Rasa——對話機(jī)器人開源框架的文章就介紹完了。如果您還想了解更多內(nèi)容，請?jiān)谟疑辖撬阉鱐OY模板網(wǎng)以前的文章或繼續(xù)瀏覽下面的相關(guān)文章，希望大家以后多多支持TOY模板網(wǎng)！
