IBM Watson Knowledge Studio-具有Role属性的实体,并从NLU api中提取它 [英] IBM Watson Knowledge Studio - Entities with Role attribute and extracting it from NLU api

查看:80
本文介绍了IBM Watson Knowledge Studio-具有Role属性的实体,并从NLU api中提取它的处理方法,对大家解决问题具有一定的参考价值,需要的朋友们下面随着小编来一起学习吧!

问题描述

我已按照以下准则使用Watson Knowledge Studio创建了自定义实体类型系统:

I have created a custom Entity Type system using Watson Knowledge Studio following these guidelines: https://www.ibm.com/watson/developercloud/doc/wks/typesystem.html

对于每种实体类型,注释者可以将属性添加到提及中,例如角色,子类型,类,类型等

For each entity type, the annotator can add attributes to a mention, e.g. role, subtype, class, type, etc.

我专门使用角色"属性来注释不同上下文中的提及.例如,这是我的实体类型系统的子集:

I am specifically using the "role" attribute, to annotate a mention in different contexts. For example, here is a subset of my entity type system:

实体-区域,症状,解决方案,客户,故障,投诉

Entities - AREA, SYMPTOM, RESOLUTION, CUSTOMER, FAULT, COMPLAINT

因此,对于一个注释为AREA的提及,我将根据提及的上下文分配角色CUSTOMER,FAULT或COMPLAINT.

Thus, for a mention annotated as AREA, I assign the role CUSTOMER, FAULT or COMPLAINT, depending on the context of the mention.

在对模型进行充分训练后,我想使用自然语言理解来提取实体类型(

When the model is sufficiently trained, I would like to use Natural Language Understanding to extract entity types (https://www.ibm.com/watson/developercloud/natural-language-understanding/api/v1/)

问题是API没有公开任何实体属性,例如角色,班级,类型等.

The problem is the API does not expose any of the entity attributes, e.g. role, class, type, etc.

因此,我的问题是,当您训练模型并希望从看不见的文本中提取实体和关系时,如何提取实体属性?如果NLU无法提取(除非您可以,但是我已经以某种方式错过了它),角色,类和提及类型的意义是什么?

My question is therefore, how does one extract the entity attributes when you've trained your model and wish to extract entities and relations from an unseen text? What is the point of role, class and mention type if NLU cannot extract it (unless you can, but I've missed it somehow)?

推荐答案

当前,正如您提到的,无法在NLU中提取实体属性,而从看不见的文本中提取实体属性的唯一方法是将ML注释器作为pre运行. -WKS中的注释器.我们正在研究以在将来增强此功能.

Currently, as you mentioned, entity attributes cannot be extracted in NLU and the only way to extract entity attributes from an unseen text would be to run ML annotator as pre-annotator within WKS. We are investigating to enhance this in future.

这篇关于IBM Watson Knowledge Studio-具有Role属性的实体,并从NLU api中提取它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!

查看全文
登录 关闭
扫码关注1秒登录
发送“验证码”获取 | 15天全站免登陆