You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: articles/cognitive-services/Translator/custom-translator/how-to-search-edit-delete-projects.md
-2Lines changed: 0 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -49,8 +49,6 @@ Custom Translator gives you the ability to edit the name and description of a pr
49
49
## Delete a project
50
50
51
51
You can delete a project when you no longer need it. Make sure the project doesn't have models in an active state such as deployed, training submitted, data processing, or deploying, otherwise, the delete operation will fail. The following steps describe how to delete a project.
52
-
53
-
54
52
1. Hover on any project record and select on the **trash bin** icon.
description: Custom Translator offers similar capabilities to what Microsoft Translator Hub does for Statistical Machine Translation (SMT), but exclusively for Neural Machine Translation (NMT) systems.
4
+
description: Custom Translator offers similar capabilities to what Microsoft Translator Hub does for Statistical Machine Translation (SMT), but exclusively for Neural Machine Translation (NMT) systems.
5
5
author: laujan
6
6
manager: nitinme
7
7
ms.service: cognitive-services
8
8
ms.subservice: translator-text
9
9
ms.date: 02/25/2022
10
10
ms.author: lajanuar
11
11
ms.topic: overview
12
-
#Customer intent: As a custom translator user, I want to understand what is Custom Translator, so that I can start using it.
13
12
---
14
13
# What is Custom Translator?
15
14
16
15
Custom Translator is a feature of the Microsoft Translator service, which enables Translator enterprises, app developers, and language service providers to build customized neural machine translation (NMT) systems. The customized translation systems seamlessly integrate into existing applications, workflows, and websites.
17
16
18
-
Translation systems built with [Custom Translator](https://portal.customtranslator.azure.ai) are available through the same cloud-based, secure, high performance, highly scalable Microsoft Translator [Text API V3](../reference/v3-0-translate.md?tabs=curl), that powers billions of translations every day.
17
+
Translation systems built with [Custom Translator](https://portal.customtranslator.azure.ai) are available through the same cloud-based, secure, high performance, highly scalable Microsoft Translator [Text API V3](../reference/v3-0-translate.md?tabs=curl) that powers billions of translations every day.
19
18
20
19
The platform enables users to build and publish custom translation systems to and from English. Custom Translator supports more than three dozen languages that map directly to the languages available for NMT. For a complete list, *see*[Translator language support](../language-support.md).
21
20
22
21
This documentation contains the following article types:
23
22
24
-
*[**Quickstarts**](./v2-preview/quickstart.md) are getting-started instructions to guide you through making requests to the service.
25
-
*[**How-to guides**](./v2-preview/how-to/create-manage-workspace.md) contain instructions for using the feature in more specific or customized ways.
23
+
*[**Quickstarts**](./v2.0/quickstart.md) are getting-started instructions to guide you through making requests to the service.
24
+
*[**How-to guides**](./v2.0/how-to/create-manage-workspace.md) contain instructions for using the feature in more specific or customized ways.
26
25
27
26
## Features
28
27
@@ -31,10 +30,10 @@ Custom Translator provides different features to build custom translation system
31
30
|Feature |Description |
32
31
|---------|---------|
33
32
|[Apply neural machine translation technology](https://www.microsoft.com/translator/blog/2016/11/15/microsoft-translator-launching-neural-network-based-translations-for-all-its-speech-languages/)| Improve your translation by applying neural machine translation (NMT) provided by Custom translator. |
34
-
|[Build systems that knows your business terminology](./v2-preview/beginners-guide.md)| Customize and build translation systems using parallel documents, that understand the terminologies used in your own business and industry. |
35
-
|[Use a dictionary to build your models](./v2-preview/how-to/train-custom-model.md#when-to-select-dictionary-only-training)| If you don't have training data set, you can train a model with only dictionary data. |
36
-
|[Collaborate with others](./v2-preview/how-to/create-manage-workspace.md#manage-workspace-settings)| Collaborate with your team by sharing your work with different people. |
37
-
|[Access your custom translation model](./v2-preview/how-to/translate-with-custom-model.md)| Your custom translation model can be accessed anytime by your existing applications/ programs via Microsoft Translator Text API V3. |
33
+
|[Build systems that knows your business terminology](./v2.0/beginners-guide.md)| Customize and build translation systems using parallel documents that understand the terminologies used in your own business and industry. |
34
+
|[Use a dictionary to build your models](./v2.0/how-to/train-custom-model.md#when-to-select-dictionary-only-training)| If you don't have training data set, you can train a model with only dictionary data. |
35
+
|[Collaborate with others](./v2.0/how-to/create-manage-workspace.md#manage-workspace-settings)| Collaborate with your team by sharing your work with different people. |
36
+
|[Access your custom translation model](./v2.0/how-to/translate-with-custom-model.md)| Your custom translation model can be accessed anytime by your existing applications/ programs via Microsoft Translator Text API V3. |
38
37
39
38
## Get better translations
40
39
@@ -50,19 +49,19 @@ If the appropriate type and amount of training data is supplied, it's not uncomm
50
49
51
50
With [Custom Translator](https://portal.customtranslator.azure.ai), training and deploying a custom system doesn't require any programming skills.
52
51
53
-
Using the secure [Custom Translator](https://portal.customtranslator.azure.ai) portal, users can upload training data, train systems, test systems, and deploy them to a production environment through an intuitive user interface. The system will then be available for use at scale within a few hours (actual time depends on training data size).
52
+
The secure [Custom Translator](https://portal.customtranslator.azure.ai) portal enables users to upload training data, train systems, test systems, and deploy them to a production environment through an intuitive user interface. The system will then be available for use at scale within a few hours (actual time depends on training data size).
54
53
55
-
[Custom Translator](https://portal.customtranslator.azure.ai) can also be programmatically accessed through a [dedicated API](https://custom-api.cognitive.microsofttranslator.com/swagger/) (currently in preview). The API allows users to manage creating or updating training through their own app or webservice.
54
+
[Custom Translator](https://portal.customtranslator.azure.ai) can also be programmatically accessed through a [dedicated API](https://custom-api.cognitive.microsofttranslator.com/swagger/). The API allows users to manage creating or updating training through their own app or webservice.
56
55
57
56
The cost of using a custom model to translate content is based on the user's Translator Text API pricing tier. See the Cognitive Services [Translator Text API pricing webpage](https://azure.microsoft.com/pricing/details/cognitive-services/translator-text-api/)
58
57
for pricing tier details.
59
58
60
59
## Securely translate anytime, anywhere on all your apps and services
61
60
62
-
Custom systems can be seamlessly accessed and integrated into any product or business workflow, and on any device, via the Microsoft Translator Text API through standard REST technology.
61
+
Custom systems can be seamlessly accessed and integrated into any product or business workflow and on any device via the Microsoft Translator Text REST API.
63
62
64
63
## Next steps
65
64
66
-
- Read about [pricing details](https://azure.microsoft.com/pricing/details/cognitive-services/translator-text-api/).
65
+
* Read about [pricing details](https://azure.microsoft.com/pricing/details/cognitive-services/translator-text-api/).
67
66
68
-
- With [Quickstart](./v2-preview/quickstart.md) learn to build a translation model in Custom Translator.
67
+
* With [Quickstart](./v2.0/quickstart.md) learn to build a translation model in Custom Translator.
Next, upload [training](training-and-model.md#training-document-type-for-custom-translator), [tuning](training-and-model.md#tuning-document-type-for-custom-translator) and [testing](training-and-model.md#testing-dataset-for-custom-translator) document sets. You can upload both [parallel](what-are-parallel-documents.md) and combo documents. You can also upload [dictionary](what-is-dictionary.md).
Copy file name to clipboardExpand all lines: articles/cognitive-services/Translator/custom-translator/v2.0/beginners-guide.md
+5-5Lines changed: 5 additions & 5 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -10,15 +10,15 @@ ms.author: lajanuar
10
10
ms.date: 02/25/2022
11
11
ms.topic: overview
12
12
---
13
-
# Custom Translator for beginners | Preview
13
+
# Custom Translator for beginners
14
14
15
15
[Custom Translator](../overview.md) enables you to a build translation system that reflects your business, industry, and domain-specific terminology and style. Training and deploying a custom system is easy and doesn't require any programming skills. The customized translation system seamlessly integrates into your existing applications, workflows, and websites and is available on Azure through the same cloud-based [Microsoft Text Translator API](../../reference/v3-0-translate.md?tabs=curl) service that powers billions of translations every day.
16
16
17
17
The platform enables users to build and publish custom translation systems to and from English. The Custom Translator supports more than three dozen languages that map directly to the languages available for NMT. For a complete list, *see*[Translator language support](../../language-support.md).
18
18
19
19
## Is a custom translation model the right choice for me?
20
20
21
-
A well-trained custom translation model provides more accurate domain-specific translations. This is because it relies on previously translated in-domain documents to learn preferred translations. Translator uses these terms and phrases in context to produce fluent translations in the target language while respecting context-dependent grammar.
21
+
A well-trained custom translation model provides more accurate domain-specific translations because it relies on previously translated in-domain documents to learn preferred translations. Translator uses these terms and phrases in context to produce fluent translations in the target language while respecting context-dependent grammar.
22
22
23
23
Training a full custom translation model requires a substantial amount of data. If you don't have at least 10,000 sentences of previously trained documents, you won't be able to train a full-language translation model. However, you can either train a dictionary-only model or use the high-quality, out-of-the-box translations available with the Text Translator API.
24
24
@@ -91,13 +91,13 @@ Tuning and test sentences are optimally representative of what you plan to trans
91
91
92
92
## How is training material processed by Custom Translator?
93
93
94
-
When you submit documents for training a custom translation system, the documents undergo a series of processing and filtering steps to prepare for training. These steps are explained below. Knowledge of the filtering process may help with understanding the sentence count displayed as well as the steps you can take to prepare training documents for training with Custom Translator.
94
+
To prepare for training, documents undergo a series of processing and filtering steps. These steps are explained below. Knowledge of the filtering process may help with understanding the sentence count displayed as well as the steps you can take to prepare training documents for training with Custom Translator.
95
95
96
96
*### Sentence alignment
97
97
98
98
If your document isn't in XLIFF, XLSX, TMX, or ALIGN format, Custom Translator aligns the sentences of your source and target documents to each other, sentence-by-sentence. Translator doesn't perform document alignment—it follows your naming convention for the documents to find a matching document in the other language. Within the source text, Custom Translator tries to find the corresponding sentence in the target language. It uses document markup like embedded HTML tags to help with the alignment.
99
99
100
-
If you see a large discrepancy between the number of sentences in the source and target documents, your source document may not be parallel or couldn't be aligned. The document pairs with a large difference (>10%) of sentences on each side warrant a second look to make sure they're indeed parallel.
100
+
If you see a large discrepancy between the number of sentences in the source and target documents, your source document may not be parallel, or couldn't be aligned. The document pairs with a large difference (>10%) of sentences on each side warrant a second look to make sure they're indeed parallel.
101
101
102
102
*### Extracting tuning and testing data
103
103
@@ -149,7 +149,7 @@ When you submit documents for training a custom translation system, the document
149
149
150
150
## How do I evaluate the results?
151
151
152
-
After your model is successfully trained, you can view the model's BLEU score and baseline model BLEU score on the model details page. We use the same set of test data to generate both the model's BLEU score and the baseline BLEU score to help you make an informed decision regarding which model would be better for your use-case.
152
+
After your model is successfully trained, you can view the model's BLEU score and baseline model BLEU score on the model details page. We use the same set of test data to generate both the model's BLEU score and the baseline BLEU score. This data will help you make an informed decision regarding which model would be better for your use-case.
Copy file name to clipboardExpand all lines: articles/cognitive-services/Translator/custom-translator/v2.0/how-to/create-manage-project.md
+4-7Lines changed: 4 additions & 7 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,7 +1,7 @@
1
1
---
2
2
title: Create and manage a project
3
3
titleSuffix: Azure Cognitive Services
4
-
description: How to create and manage a project in the Azure Cognitive Services Custom Translator Preview.
4
+
description: How to create and manage a project in the Azure Cognitive Services Custom Translator.
5
5
author: laujan
6
6
manager: nitinme
7
7
ms.service: cognitive-services
@@ -11,18 +11,15 @@ ms.author: lajanuar
11
11
ms.topic: how-to
12
12
---
13
13
14
-
# Create and manage a project | Preview
15
-
16
-
> [!IMPORTANT]
17
-
> Custom Translator v2.0 is currently in public preview. Some features may not be supported or have constrained capabilities.
14
+
# Create and manage a project
18
15
19
16
A project contains translation models for one language pair. Each project includes all documents that were uploaded into that workspace with the correct language pair.
20
17
21
18
Creating a project is the first step in building and publishing a model.
22
19
23
20
## Create a project
24
21
25
-
1. After you sign-in, your default workspace is loaded. To create a project in different workspace, select **My workspaces**, then select a workspace name.
22
+
1. After you signin, your default workspace is loaded. To create a project in different workspace, select **My workspaces**, then select a workspace name.
26
23
27
24
1. Select **Create project**.
28
25
@@ -43,7 +40,7 @@ Creating a project is the first step in building and publishing a model.
43
40
44
41
- Don't use a label if you're building systems for one domain only.
45
42
46
-
- A project label is not required and not helpful to distinguish between language pairs.
43
+
- A project label isn't required and not helpful to distinguish between language pairs.
47
44
48
45
- You can use the same label for multiple projects.
0 commit comments