共同参考分辨率,一个例子 [英] Co-Reference resolution, an example
问题描述
我确信LUIS是一个很好的意图识别平台,它会支持这个功能,比如使用自定义建模或培训,但我无法弄清楚如何实现这一点。因此,寻找一些指导或方向,询问这是否是使用LUIS可能的
,如果是,如果可以给出一些提示或方向。
E.G:杰夫在学校学习。他今天没去上学。
在上面的陈述中,如果我要进行实体匹配,Jeff和他代表同一个实体逻辑。但是通过LUIS内置的人名实体,只有Jeff被识别为名称。而"他"则是"他"。这也指杰夫未被识别为
或被认可。
我如何才能在LUIS中实现这一目标?
$
  ;
你在谈论 检测潜在的亵渎性并帮助检查个人身份信息(PII)。
这有助于集成到Bots中,使Bot能够对亵渎行为作出反应,或者如果用户共享PII信息。例如,如果检测到PII信息,Bot可以道歉并传递给人或不存储遥测记录。
请参考以下链接:https://docs.microsoft.com/en-us /azure/bot-service/bot-builder-enterprise-template-overview-detail?view=azure-bot-service-4.0#content-moderator
https: //docs.microsoft.com/en-us/azure/cognitive-services/content-moderator/overview
问候,
Yutong
I am sure that LUIS being such a great platform for intent recognition, it would support this feature say using custom modeling or training, but I am unable to figure out how to make this happen. Hence looking for some guide or direction asking if this is possible using LUIS and if so, if some hints or direction can be given.
E.G: Jeff studies in a school. He did not go to school today.
In the above statement, if I were to do entity match, Jeff and He represents the same entity logically. But via LUIS inbuilt person name entity only Jeff gets recognized as a name. While "He" which is also referring to Jeff is not identified or recognized.
How can I make this happen in LUIS?
Hi,
Are you talking about the detection of potential profanity and helps check for personally identifiable information (PII). This can be helpful to integrate into Bots enabling a Bot to react to profanity or if the user shares PII information. For example, a Bot can apologise and hand-off to a human or not store telemetry records if PII information is detected.
Please refer to following link: https://docs.microsoft.com/en-us/azure/bot-service/bot-builder-enterprise-template-overview-detail?view=azure-bot-service-4.0#content-moderator
https://docs.microsoft.com/en-us/azure/cognitive-services/content-moderator/overview
Regards,
Yutong
这篇关于共同参考分辨率,一个例子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IT屋!