在示例言语中标记机器学习的实体Label machine-learned entity in an example utterance

在示例言语中标记实体可为 LUIS 提供示例,其中包含实体的示例,以及实体可以在言语中出现的位置的示例。Labeling an entity in an example utterance gives LUIS an example of what the entity is and where the entity can appear in the utterance.

标记机器学习实体Labeling machine-learned entity

不妨使用此短语:hi, please I want a cheese pizza in 20 minutesConsider the phrase, hi, please I want a cheese pizza in 20 minutes.

  1. 选择最左侧的文本,然后选择实体最右侧的文本,接下来选择想要进行标记的实体(在本例中为“完整订单”)。Select the left-most text, then select the right-most text of the entity, then pick the entity you want to label with, in this case Complete Order. 下图中标记了完成顺序 。The complete order is labeled in the following image.

    标记完整的机器学习实体Label complete machine-learned entity

  2. 从弹出窗口中选择实体。Select the entity from the pop-up window. 标记的完整的比萨订单实体包括所有被标记的单词(从左到右,英语)。The labeled complete pizza order entity includes all words (from left to right in English) that are labeled.

查看标记的文本Review labeled text

进行标记后,查看示例言语,并确保选定的一段文本中的选定实体带有下划线。After labeling, review the example utterance and ensure the selected span of text has been underlined with the chosen entity. 实线指示文本已被标记。The solid line indicates the text has been labeled.

标记的完整机器学习实体Labeled complete machine-learned entity

确认预测的实体Confirm predicted entity

如果这一段文本被虚线框框起来,并且实体名称位于言语上方,则表示已预测文本,但_尚未标记_。If there is a dotted-lined box around the span of text and the entity name is above the utterance, it indicates the text is predicted but not labeled yet. 若要将预测转变为标签,依次选择该言语所在的行和“确认实体预测” 。To turn the prediction into a label, select the utterance row, then select Confirm entity predictions.

预测完整的机器学习实体Predict complete machine-learned entity

或者,可选择文本上方的实体名称,然后从显示的菜单中选择“确认预测” 。Alternatively, you could select the entity name above the text, then select Confirm Prediction from the menu that appears.

使用菜单预测完整的机器习得实体Predict complete machine-learned entity with menu

通过使用实体调色板光标进行绘制来标记实体Label entity by painting with entity palette cursor

实体调色板提供之前的标记体验的替代方法。The entity palette offers an alternative to the previous labeling experience. 它允许对文本进行画笔处理,使其能够立即使用实体进行标记。It allows you to brush over text to instantly label it with an entity.

  1. 通过选择言语表右上方的荧光笔图标来打开实体调色板。Open the entity palette by selecting on the Highlighter icon at the top right of the utterance table.

    机器学习实体的实体调色板Entity palette for machine-learned entity

  2. 选择实体组件。Select the entity component. 此操作采用可视方式指示新的光标。This action is visually indicated with a new cursor. 当你在门户中移动时,光标将跟随鼠标。The cursor follows the mouse as you move in the portal.

    机器学习实体的实体调色板Entity palette for machine-learned entity

  3. 在示例言语中,用光标绘制 实体。In the example utterance, paint the entity with the cursor.

    机器学习实体的实体调色板Entity palette for machine-learned entity

标记机器习得实体的子组件Labeling subcomponents of a machine learned entity

实体中子组件的标记方式与顶级实体的标记方式完全相同。Subcomponents in entities are labeled exactly the same way as top level entities. 选择文本时,弹出窗口中可用的实体是相对于文本出现的上下文而言的。When selecting text, the entities available in the pop-up window are relative to the context in which the text appears. 例如,如果你有一个 5 级机器习得实体,并选择标记为第 1 级和第 2 级的文本(通过示例言语下已标记的实体名称表示),则弹出窗口中可用的实体会被限制为第 3 级组件的上下文。For example, if you have a 5-level machine-learned entity, and you are selecting text that has been labeled with the 1st and 2nd levels (indicated by a labeled entity name under the example utterance), the entities available in the pop-up window are limited to the context of components of the 3rd level. 若要使用其他实体标记文本,请选择“标记为其他实体”选项 。To label the text with other entities, select Label as another entity option.

机器学习实体的实体调色板Entity palette for machine-learned entity

仅当父组件也进行标记时,才可对子组件进行标记。Subcomponents can be labeled only if the parent is also labeled.

标记实体角色Labeling entity roles

实体角色使用实体调色板进行标记。Entity roles are labeled using the entity palette.

  1. 在“意向详细信息”页上,从上下文工具栏中选择“实体调色板” 。In the Intent detail page, select the Entity palette from the context toolbar.
  2. 在实体调色板打开后,从实体列表中选择实体。After the Entity palette opens, select the entity from the list of entity.
  3. 转到“实体检查器”,选择现有角色或创建新角色 。Move to the Entity inspector, and either select an existing role or create a new role.
  4. 在示例言语文本中,使用实体角色标记文本。In the example utterance text, label the text with the entity role.

取消标记实体Unlabel entities

若要取消标记实体,请选择文本下方的实体名称,然后选择“取消标记” 。To unlabel an entity, select the entity name underneath the text and select Unlabel. 如果尝试取消标记的实体具有已标记的子组件,则必须先取消标记子组件。If the entity you are trying to unlabel has labeled subcomponents, then the subcomponents must be unlabeled first.

使用实体调色板编辑标签Editing labels using the entity palette

如果在进行标记时出错,则可使用实体调色板轻松实现快速编辑。If you make a mistake while labeling, the entity palette is an easy tool that allows for quick edits. 例如,如果某个实体标签错误地多标记了一个字词,且其具有已标记的子组件,则可使用实体调色板来对所需的较短字词范围进行画笔处理。For example, if an entity label spans an extra word by mistake, and it already has labeled subcomponents, then you can use the entity palette to brush over the required shorter span of words.

例如:For example:

  1. “披萨类型”子组件跨越“cheese pizza with”,其中包含多余的错误字词“with”Pizza Type subcomponent spans "cheese pizza with" which includes an extra incorrect word -- "with"

    机器学习实体的实体调色板Entity palette for machine-learned entity

  2. 使用实体调色板选取“披萨类型”并对“cheese pizza”进行画笔处理。Use the entity palette to pick Pizza Type and brush over "cheese pizza". 结果就是现在仅“cheese pizza”标记为“披萨类型”。The outcome is that only cheese pizza is labeled as Pizza Type now.

    机器学习实体的实体调色板Entity palette for machine-learned entity

用于匹配文本实体的标签Labels for matching-text entities

匹配文本实体包括预生成实体、正则表达式实体、列表实体和 pattern.any 实体。Matching-text entities include prebuilt entities, regular expression entities, list entities, and pattern.any entities. 这些实体由 LUIS 自动标记,因此无需用户手动标记它们。These are automatically labeled by LUIS so they are not required to be manually labeled by users.

实体预测错误Entity prediction errors

实体预测错误表示预测的实体与标记的实体不匹配。Entity prediction errors indicate the predicted entity doesn't match the labeled entity. 这通过言语旁边的警告指示器直观显示。This is visualized with a caution indicator next to the utterance.

机器学习实体的实体调色板Entity palette for machine-learned entity