|
2 | 2 | title: Label entity example utterance |
3 | 3 | description: Learn how to label a machine-learned entity with subcomponents in an example utterance in an intent detail page of the LUIS portal. |
4 | 4 | ms.topic: conceptual |
5 | | -ms.date: 04/14/2020 |
| 5 | +ms.date: 05/17/2020 |
6 | 6 | #Customer intent: As a new user, I want to label a machine-learned entity in an example utterance. |
7 | 7 | --- |
8 | 8 |
|
9 | 9 | # Label machine-learned entity in an example utterance |
10 | 10 |
|
11 | 11 | 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. |
12 | 12 |
|
13 | | -## Labeling machine-learned entity |
| 13 | +## Label example utterances from the Intent detail page |
14 | 14 |
|
15 | | -Consider the phrase, `hi, please I want a cheese pizza in 20 minutes`. |
| 15 | +1. Sign in to the [LUIS portal](https://www.luis.ai), and select your **Subscription** and **Authoring resource** to see the apps assigned to that authoring resource. |
| 16 | +1. Open your app by selecting its name on **My Apps** page. |
| 17 | +1. Select the Intent that has the example utterances you want to label for extraction with an entity. |
| 18 | +1. Select the text you want to label then select the entity. |
16 | 19 |
|
17 | | -1. 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. The _complete order_ is labeled in the following image. |
| 20 | +## Label with the Entity Palette visible |
18 | 21 |
|
19 | | - > [!div class="mx-imgBorder"] |
20 | | - >  |
21 | | -
|
22 | | -1. Select the entity from the pop-up window. The labeled complete pizza order entity includes all words (from left to right in English) that are labeled. |
23 | | - |
24 | | -## Review labeled text |
| 22 | +After you've planned your schema with entities, keep the **Entity palette** visible while labeling. The **Entity palette** is a reminder of what your entities you planned to extract. |
25 | 23 |
|
26 | | -After labeling, review the example utterance and ensure the selected span of text has been underlined with the chosen entity. The solid line indicates the text has been labeled. |
| 24 | +To access the **Entity Palette**, select the **@** symbol in the contextual toolbar above the example utterance list. |
27 | 25 |
|
28 | 26 | > [!div class="mx-imgBorder"] |
29 | | ->  |
| 27 | +>  |
30 | 28 |
|
31 | | -## Confirm predicted entity |
| 29 | +## Label entity from in-place menu |
32 | 30 |
|
33 | | -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_. To turn the prediction into a label, select the utterance row, then select **Confirm entity predictions**. |
| 31 | +Consider the example utterance, `hi, please I want a cheese pizza in 20 minutes`. |
34 | 32 |
|
35 | | -> [!div class="mx-imgBorder"] |
36 | | ->  |
| 33 | +1. Select the left-most text, then select the right-most text of the entity, then from the in-place menu, pick the entity you want to label with. |
37 | 34 |
|
38 | | -Alternatively, you could select the entity name above the text, then select **Confirm Prediction** from the menu that appears. |
| 35 | + > [!div class="mx-imgBorder"] |
| 36 | + >  |
39 | 37 |
|
40 | | -> [!div class="mx-imgBorder"] |
41 | | ->  |
42 | 38 |
|
43 | | -## Label entity by painting with entity palette cursor |
| 39 | +## Label entity from Entity Palette |
44 | 40 |
|
45 | 41 | The entity palette offers an alternative to the previous labeling experience. It allows you to brush over text to instantly label it with an entity. |
46 | 42 |
|
47 | | -1. Open the entity palette by selecting on the Highlighter icon at the top right of the utterance table. |
48 | | - |
49 | | - > [!div class="mx-imgBorder"] |
50 | | - >  |
51 | | -
|
52 | | -2. Select the entity component. This action is visually indicated with a new cursor. The cursor follows the mouse as you move in the portal. |
| 43 | +1. Open the entity palette by selecting on the **@** symbol at the top right of the utterance table. |
53 | 44 |
|
54 | | - > [!div class="mx-imgBorder"] |
55 | | - >  |
| 45 | +2. Select the entity from the palette that you want to label. This action is visually indicated with a new cursor. The cursor follows the mouse as you move in the LUIS portal. |
56 | 46 |
|
57 | 47 | 3. In the example utterance, _paint_ the entity with the cursor. |
58 | 48 |
|
59 | 49 | > [!div class="mx-imgBorder"] |
60 | 50 | >  |
61 | 51 |
|
62 | | -## Labeling subcomponents of a machine learned entity |
| 52 | +## Adding entity as a feature from the Entity Palette |
63 | 53 |
|
64 | | -Subcomponents in entities are labeled exactly the same way as top level entities. When selecting text, the entities available in the pop-up window are relative to the context in which the text appears. 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. To label the text with other entities, select **Label as another entity** option. |
| 54 | +The Entity Palette's lower section allows you to add features to the currently selected entity. You can select from all existing entities and phrase lists or create a new phrase list. |
65 | 55 |
|
66 | 56 | > [!div class="mx-imgBorder"] |
67 | | ->  |
68 | | -
|
69 | | -Subcomponents can be labeled only if the parent is also labeled. |
| 57 | +>  |
70 | 58 |
|
71 | 59 | ## Labeling entity roles |
72 | 60 |
|
73 | | -Entity roles are labeled using the entity palette. |
| 61 | +Entity roles are labeled using the **Entity palette**. |
74 | 62 |
|
75 | 63 | 1. In the Intent detail page, select the **Entity palette** from the context toolbar. |
76 | 64 | 1. After the Entity palette opens, select the entity from the list of entity. |
77 | | -1. Move to the **Entity inspector**, and either select an existing role or create a new role. |
| 65 | +1. Below the list of entities, select an existing role. |
78 | 66 | 1. In the example utterance text, label the text with the entity role. |
79 | 67 |
|
80 | | -## Labeling for punctuation |
| 68 | +## Review labeled text |
81 | 69 |
|
82 | | -You do not need to label for punctuation. Use [application settings](luis-reference-application-settings.md) to control if punctuation impacts utterance predictions. |
| 70 | +After labeling, review the example utterance and ensure the selected span of text has been underlined with the chosen entity. The solid line indicates the text has been labeled. |
83 | 71 |
|
84 | | -## Unlabel entities |
| 72 | +> [!div class="mx-imgBorder"] |
| 73 | +>  |
85 | 74 |
|
86 | | -To unlabel an entity, select the entity name underneath the text and select **Unlabel**. If the entity you are trying to unlabel has labeled subcomponents, then the subcomponents must be unlabeled first. |
| 75 | +## Confirm predicted entity |
87 | 76 |
|
88 | | -## Editing labels using the entity palette |
| 77 | +If there is a dotted-lined box around the span of text, it indicates the text is predicted but _not labeled yet_. To turn the prediction into a label, select the utterance row, then select **Confirm entities** from the contextual toolbar. |
89 | 78 |
|
90 | | -If you make a mistake while labeling, the entity palette is an easy tool that allows for quick edits. 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. |
| 79 | +## Relabeling over existing entities |
91 | 80 |
|
92 | | -For example: |
| 81 | +If you relabel text that is already labeled, LUIS may split or merge existing labels. |
93 | 82 |
|
94 | | -1. Pizza Type subcomponent spans "cheese pizza with" which includes an extra incorrect word -- "with" |
| 83 | +## Labeling for punctuation |
95 | 84 |
|
96 | | - > [!div class="mx-imgBorder"] |
97 | | - >  |
| 85 | +You do not need to label for punctuation. Use [application settings](luis-reference-application-settings.md) _word forms_ to control if punctuation impacts utterance predictions. |
98 | 86 |
|
99 | | -2. Use the entity palette to pick Pizza Type and brush over "cheese pizza". The outcome is that only cheese pizza is labeled as Pizza Type now. |
| 87 | +## Unlabel entities |
100 | 88 |
|
101 | | - > [!div class="mx-imgBorder"] |
102 | | - >  |
| 89 | +> [!NOTE] |
| 90 | +> Only machine learned entities can be unlabeled. |
| 91 | +
|
| 92 | +To unlabel an entity, select the entity and select **Unlabel** from the in-place menu. |
| 93 | + |
| 94 | +> [!div class="mx-imgBorder"] |
| 95 | +>  |
| 96 | +
|
| 97 | +## Automatic labeling for parent and child entities |
| 98 | + |
| 99 | +If you are labeling a parent entity, any subentity that can be predicted based on the currently trained version, will be labeled. |
| 100 | + |
| 101 | +If you are labeling for a subentity, the parent will be labeled automatically. |
103 | 102 |
|
104 | | -## Labels for matching-text entities |
| 103 | +## Automatic labeling for non-machine learned entities |
105 | 104 |
|
106 | | -Matching-text entities include prebuilt entities, regular expression entities, list entities, and pattern.any entities. These are automatically labeled by LUIS so they are not required to be manually labeled by users. |
| 105 | +Non-machine learned entities include prebuilt entities, regular expression entities, list entities, and pattern.any entities. These are automatically labeled by LUIS so they are not required to be manually labeled by users. |
107 | 106 |
|
108 | 107 | ## Entity prediction errors |
109 | 108 |
|
|
0 commit comments