问题描述
我正在使用rasa构建机器人来回答用户的问题，但是我遇到了问题.
I’m building bot using rasa to response for user’s questions and I have an issue.
Rasa使我对与意图示例完全无关的邮件充满信心.
Rasa gives me high level of confidence for messages that are completely not related to intent’s examples.
我有与医疗有关的意图，但是诸如我喜欢咖啡"之类的信息比与之相关的信息给我更多的信心.另外，诸如"laj jfias jjlas fe"之类的随机字符消息也使我充满信心.
I have medical-related intents but message like "I like coffee" gives me even more confidence than messages related. Also, random chars messages like "laj jfias jjlas fe" also give me high confidence.
任何人都可以给我提示如何解决此问题吗?我在哪里可以找到错误?
Could anyone give me a hint how to fix this? Where can I look for a bug?
这是我的配置:
language: "en"
pipeline:
- name: "nlp_spacy"
- name: "tokenizer_spacy"
- name: "intent_entity_featurizer_regex"
- name: "intent_featurizer_spacy"
- name: "ner_crf"
- name: "ner_synonyms"
- name: "intent_classifier_sklearn"
推荐答案
强制分类到您的意图之一似乎是问题所在.解决它的一种方法可能是这样的:
Forced classification into one of your intents, seems to be the issue.One way to solve it can be like this:
-
添加一些与您的域&无关的示例出于某种意图添加它们，例如
your_fallback_intent
为your_fallback_intent
这将使nlu在your_fallback_intent
如果您仍然遇到问题，请在评论中添加详细信息.
pls add details in comment if you still face the issue.
这篇关于拉沙不相关邮件的置信度得分错误的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持！