我想实现两个阶段的后备策略,我遵循了这个article
这是config.yml
language: en
pipeline:
# other policies
- name: DIETClassifier
epochs: 100
entity_recognition: False
- name: ResponseSelector
epochs: 100
- name: FallbackClassifier
threshold: 0.7
policies:
- name: TEDPolicy
max_history: 10
epochs: 20
- name: AugmentedMemoizationPolicy
max_history: 6
- name: RulePolicy在rules.yml中添加了规则-
rule: Implementation of the Two-Stage-Fallback
steps: - intent: nlu_fallback
- action: action_two_stage_fallback
- active_loop: action_two_stage_fallback和domain.yml格式的响应
responses:
utter_ask_rephrase:
- text: I'm sorry, I didn't quite understand that. Could you rephrase? 在意图上,信心告别0.23,它是在执行告别,而不是后退政策。
我是不是遗漏了什么?
发布于 2021-03-11 12:59:18
我需要提几个RulePolicy的参数
- name: RulePolicy
core_fallback_threshold: 0.3
core_fallback_action_name: "action_default_fallback"
enable_fallback_prediction: True现在这个方法起作用了
https://stackoverflow.com/questions/66558761
复制相似问题