Data Processing Is Wrong

[ZephyrChenzf]

I find the kvret processing is wrong because you let all of the requests is empty in the function, and the de_degree will always be 0.

[ZephyrChenzf]

why use the informable in kvretz data processing?

[ZephyrChenzf]

There is a serious problem here. In your model, the generated reply is used as the input for the next round. When testing, you should use the generated response, and you directly use the existing reply of the training data. This is wrong.

[shizhediao]

I find the kvret processing is wrong because you let all of the requests is empty in the function, and the de_degree will always be 0.

could you specify which function or what's the line number? just a reminder: For evaluation, entity match rate determines if a system can generate all correct constraints(not requests) to search the indicated entities of the user.

[ZephyrChenzf]

I find the kvret processing is wrong because you let all of the requests is empty in the function, and the de_degree will always be 0.

could you specify which function or what's the line number? just a reminder: For evaluation, entity match rate determines if a system can generate all correct constraints(not requests) to search the indicated entities of the user.

you has changed the de_degree function,I will try it again a few days later, and try to use and check it.thank you!

[hulumei123]

    informable = {
        'weather': ['date','location','weather_attribute'], 
        'navigate': ['poi_type','distance'],
        'schedule': ['event']
    }

    requestable = {
        'weather': ['weather_attribute'],
        'navigate': ['poi','traffic','address','distance'],
        'schedule': ['event','date','time','party','agenda','room'] 
    }

请问你informable和requestable中的字段是如何确定的？为什么列表中一些实体有而一些实体没有？比如说：'date'存在于informable的'weather'中，而不存在于requestable的'weather‘中。请问能解释一下确定这些实体的依据吗？

[hulumei123]

为什么代码中的informable和requestable跟论文中描述的不太一样？请问如何确定informable和requestable中的实体？