通过学习来改进与每个用户对话的Microsoft ChatBot的方法? [英] Approaches to improve Microsoft ChatBot with each user conversation by learning from it?

查看:42
本文介绍了通过学习来改进与每个用户对话的Microsoft ChatBot的方法?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

我正在使用LUIS构建用于自然语言处理的Microsoft ChatBot.我希望LUIS通过学习针对已确定意图的新话语来进行改进.

I am building a Microsoft ChatBot using LUIS for natural language processing. I would like LUIS to improve by learning new utterences for the intents identified.

例如,如果我的问候"意图有话语嗨",你好",你好,你好吗?",则下次遇到你好吗?"时,它可能会预测该意图为问候语的准确性较低.如果将这种话语作为意图的一部分来学习,那么将来,这种话语将以更高的准确度进行预测,并且还将帮助我们识别出更接近这种话语的话语.

For example, if my 'Greeting' intent has utterences 'Hi', 'Hello', 'Hello, how are you?', the next time it encounters 'How are you?', it may predict the intent as 'Greeting' with a low accuracy. If that utterance is learnt as part of the intent, then in future, this utterence will be predicted with better accuracy and also help us in recognizing utterences closer to this utterence.

学习可以基于:

  1. 已识别出意图的所有输入. (我知道这会导致错误的学习).
  2. 由LUIS标识并由用户或代理实时或稍后离线验证的输入.
  3. 确定正确/错误的输入,但稍后由代理或支持团队通过更简单的UI进行验证和更正.
  1. All input for which intent was identified. (I understand this can cause wrong learnings).
  2. Inputs identified by LUIS and verified by user or agent real-time or later offline.
  3. Inputs identified right/wrong but verified and corrected by the agent or support team later via an easier UI.

我了解LUIS给出了一个建议的建议"选项卡,其中涉及了第3点.我试图了解如何通过最少的用户干预来使这种学习自动化.

I understand LUIS gives a 'Suggested Utterences' tab which takes care of point 3. I am trying to understand how we can automate this learning by minimal user intervention.

项目中使用的各种方法是什么?

What are the various approaches used in projects?

推荐答案

有趣!我借助LUIS编程API完成了一个与此类似的项目.没有方法可以自动执行此任务.代理人应支持LUIS模型以识别新的话语,并针对主要意图指导它们,或为它们创建新的意图. 您可以使用我提到的编程API来为此任务构建自己的应用程序,而不必使用它们提供的UI. https://westus.dev.cognitive.microsoft.com/docs/services/5890b47c39e2bb17b84a55ff/operations/5890b47c39e2bb052c5b9c2f

Interesting! I've done a project similar to this by getting aid of LUIS programmatic API. There's no approach that can do this task automatically. An agent should support the LUIS model to identify the new utterances and direct them for the prevailing intents or create new intents for them. Rather than going for the UI they providing, you can build your own application for this task using the programmatic API I mentioned. https://westus.dev.cognitive.microsoft.com/docs/services/5890b47c39e2bb17b84a55ff/operations/5890b47c39e2bb052c5b9c2f

这篇关于通过学习来改进与每个用户对话的Microsoft ChatBot的方法?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