意图识别 聊天机器人_如何解决聊天机器人中的意图冲突

意图识别 聊天机器人

介绍 (Introduction)

…overlap in intent training examples might be confusing your chatbot.

…意图培训示例中的重叠内容可能会使您的聊天机器人感到困惑。

These overlaps are really conflicts, which can exist between two, three or more separate intents.

这些重叠实际上是冲突，可以存在于两个，三个或更多单独的意图之间。

Once your chatbot grows in the number of intents, and also the number of examples for each intent, finding overlaps or conflicts become harder.

一旦您的聊天机器人的意图数量以及每种意图的示例数量增加，发现重叠或冲突就变得更加困难。

The basic chatobt structure is on the left, with a list on twelve intents.

最基本的chatobt结构在左侧，其中包含十二个意图的列表。

Often the approach is just to add more examples, which most probably will just add to the confusion. While the solution is not a lack of training data or examples, but conflicts within those examples.

通常，方法只是添加更多示例，而这很可能只会增加混乱。 虽然解决方案不是缺少训练数据或示例，但这些示例之间存在冲突。

It does make sense to segment the examples clearly per intent, but overlaps might not be that easy to spot.

按照意图清楚地细分示例确实很有意义，但是重叠可能不那么容易发现。

This might very well be the case if a larger team is working on the chatbot and adding example phrases from conversations in an attempt to improve accuracy.

如果较大的团队正在研究聊天机器人并从对话中添加示例短语以试图提高准确性，则可能会非常适合。

Overlaps can easily be created in such a scenario and the whole attempt to improve the bot will in fact cause a degradation of the quality and clarity of user intent recognition.

在这种情况下，很容易产生重叠，而对改进bot的整个尝试实际上将导致质量和用户意图识别清晰度下降。

Hence detecting these conflicts become paramount in larger teams and organizations. You might have hundreds or thousands of intents each with a number of examples. This is why automation of this process is key.

因此，在较大的团队和组织中，检测这些冲突变得至关重要。 您可能有成百上千个意图，其中包含许多示例。 这就是为什么该过程的自动化是关键的原因。

追踪冲突 (Tracking Conflicts)

The ideal would be not to have a manual process of picking up conflicts, but rather a process which surfaces conflict real-time as they occur. Too many chatbot teams learn from errors and vulnerabilities in customer conversation data and monthly reports.

理想的做法不是要有一个手动处理冲突的过程，而是要在冲突发生时实时显示冲突的过程。 太多的聊天机器人团队从客户对话数据和月度报告中的错误和漏洞中学习。

Conflicts should be checked for in real-time continuously, or when updates are committed.

应该连续实时地或在提交更新时检查冲突。

How would these conflicts be managed in a real-word scenario? Here is a short tutorial…

在真实情况下如何处理这些冲突？ 这是一个简短的教程……

IBM Watson Assistant: List of Intents and the Conflict Count is visible in the Conflicts Column

IBM Watson Assistant：“冲突”列中显示了意图列表和“冲突计数”

This is an image of the IBM Watson Assistant Intent console. With the name, description and date modified, you will see how many example utterances each intent has.

这是IBM Watson Assistant Intent控制台的图像。 修改名称，描述和日期后，您将看到每个意图有多少示例话语。

Also, you will see a Conflicts column.

此外，您还将看到“ 冲突”列。

Within the Intent the Phrases Creating a Conflict is Marked

在意图内标记了造成冲突的短语

Once you click on the intent marked with a conflict, you will see the list of user examples, also referred to as utterance samples. And the problematic utterance is marked with a button to action the resolution.

单击标记有冲突的意图后，您将看到用户示例列表，也称为话语样本。 出现问题的话语用按钮标记，以控制分辨率。

不同类型的意图冲突 (Different Types of Intent Conflicts)

There are two types of conflicts;

有两种类型的冲突：

• Direct and

  直接和

• Indirect conflicts.

  间接冲突。

Direct conflicts are fairly easy to pick up. This is where two or more intents having the exact same example utterance; verbatim.

直接冲突很容易解决。 这是两个或更多个意图具有完全相同的示例话语的地方； 逐字。

Indirect conflicts are harder to detect and this is where machine learning plays a role. There might be user examples informing different intents which are very similar in meaning and sentence construction, but at a glance seem different. The removal of these vulnerabilities go a long way in improving your conversational interface’s accuracy.

间接冲突更难发现，这就是机器学习发挥作用的地方。 可能会有一些用户示例通知了不同的意图，这些意图在含义和句子结构上非常相似，但乍一看似乎有所不同。 消除这些漏洞对于提高会话界面的准确性大有帮助。

内置冲突解决 (Built-In Conflict Resolution)

Here again is an example from IBM Watson Assistant showing how this can work in practice.

这又是来自IBM Watson Assistant的示例，展示了如何在实践中工作。

You can see in the example below the two intents side by side. In this example the conflict is the same utterance word for word, verbatim.

您可以在示例中并排看到以下两个意图。 在这个例子中，冲突是逐字逐字的相同话语。

What is quite useful is the Similar Examples. Similar examples are typically not conflicts; they are additional examples that are displayed to help you better understand the meaning of each intent. And hence guide you in your decision in removing the utterance from the right intent.

非常有用的是“ 类似示例”。 类似的例子通常不是冲突。 它们是显示的其他示例，可以帮助您更好地理解每个意图的含义。 因此，引导您做出从正确意图中消除发声的决定。

Watson’s Conflict Resolution Interface

沃森的冲突解决界面

From the similar examples give here, it is clear that the example in conflict needs to be removed from the #Customer_Care_Appointment.

从此处给出的类似示例中可以明显看出，需要将冲突示例从#Customer_Care_Appointment中删除。

Confirmation of Saved Changes

确认已保存的更改

Clarity needs to be established when managing example utterances and having a set of examples can assist in this process.

管理示例话语时需要建立清晰性，并具​​有一组示例可以帮助此过程。

The examples are enough for you to create a mental picture of what embodies the intent.

这些示例足以使您对意图的精神印象。

Once the change is committed, a confirmation message is displayed and you can test your chatbot again.

提交更改后，将显示一条确认消息，您可以再次测试您的聊天机器人。

结论 (Conclusion)

There is this commonly held belief that the amount of data you throw at your chatbot yields a direct and proportional improvement in the conversational experience.

人们普遍认为，您在聊天机器人上抛出的数据量会直接和成比例地改善对话体验。

This cannot be further from the truth. Training data needs to be well thought through, segmented and meaningful.

这与事实相去甚远。 培训数据需要经过深思熟虑，细分且有意义。

在这里阅读更多… (Read More Here…)

翻译自: https://medium.com/@CobusGreyling/how-to-resolve-intent-conflicts-within-your-chatbot-74f567d30d48

意图识别 聊天机器人