Skip to content

Commit 3e5c860

Browse files
committed
updating from release branch
1 parent f30212d commit 3e5c860

File tree

55 files changed

+672
-698
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

55 files changed

+672
-698
lines changed

articles/ai-services/translator/custom-translator/azure-ai-foundry/beginners-guide.md

Lines changed: 19 additions & 19 deletions
Original file line numberDiff line numberDiff line change
@@ -1,32 +1,32 @@
11
---
2-
title: Azure AI Translator Custom Translation for beginners
2+
title: Azure AI Translator custom translation for beginners
33
titleSuffix: Azure AI services
4-
description: A user guide for understanding the end-to-end customized machine translation process.
4+
description: User guide for understanding the end-to-end customized machine translation process using Azure AI Foundry.
55
author: laujan
66
manager: nitinme
77
ms.service: azure-ai-translator
88
ms.author: lajanuar
9-
ms.date: 01/27/2025
9+
ms.date: 05/19/2025
1010
ms.topic: overview
1111
---
1212

13-
# Azure AI Translator Custom Translation for beginners
13+
# Azure AI Translator custom translation for beginners
1414

15-
[Custom Translation](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 Translation API](../reference/v3-0-translate.md?tabs=curl) service that powers billions of translations every day.
15+
[Custom translation](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 Translation API](../../text-translation/reference/v4/translate-api.md) service that powers billions of translations every day.
1616

17-
[Custom Translation](overview.md) empowers you to build a translation system that truly captures your business's unique language, industry terminology, and domain-specific style. With an intuitive interface, training, testing, and deploying your custom model is simple and requires no programming expertise. Seamlessly integrate your tailored translation system into your existing applications, workflows, and websites—all backed by the cloud-based [Azure AI Translator Text Translation API](../reference/v3-0-translate.md?tabs=curl) service that powers billions of translations each day.
17+
[Custom translation](overview.md) empowers you to build a translation system that truly captures your business's unique language, industry terminology, and domain-specific style. With an intuitive interface, training, testing, and deploying your custom model is simple and requires no programming expertise. Seamlessly integrate your tailored translation system into your existing applications, workflows, and websites—all backed by the cloud-based [Azure AI Translator Text Translation API](../../text-translation/reference/v4/translate-api.md?tabs=curl) service that powers billions of translations each day.
1818

19-
The platform enables users to build and publish custom translation systems to and from English. The Custom Translator supports more than 100 languages that map directly to the languages available for Neural machine translation (NMT). For a complete list, *see* [Translator language support](../language-support.md).
19+
The platform enables users to build and publish custom translation systems to and from English. The Custom Translator supports more than 100 languages that map directly to the languages available for Neural machine translation (NMT). For a complete list, *see* [Translator language support](../../../language-support.md).
2020

2121
## Is a custom translation model the right choice for you?
2222

23-
A well-trained custom translation model excels at delivering accurate, domain-specific translations by learning from your previously translated in-domain documents. This approach ensures that your specialized terms and phrases are used in context, producing fluent, natural translations that respect the target languages grammatical nuances.
23+
A well-trained custom translation model excels at delivering accurate, domain-specific translations by learning from your previously translated in-domain documents. This approach ensures that your specialized terms and phrases are used in context, producing fluent, natural translations that respect the target language's grammatical nuances.
2424

25-
Keep in mind that developing a full custom translation model requires a substantial amount of training data—typically at least 10,000 parallel sentences. If you dont have enough data to train a comprehensive model, you might consider building a dictionary-only model to capture essential terminology, or you can rely on the high-quality, out-of-the-box translations offered by the Text Translation API.
25+
Keep in mind that developing a full custom translation model requires a substantial amount of training data—typically at least 10,000 parallel sentences. If you don't have enough data to train a comprehensive model, you might consider building a dictionary-only model to capture essential terminology, or you can rely on the high-quality, out-of-the-box translations offered by the Text Translation API.
2626

27-
Ultimately, if you need translations that reflect your industrys specific language and you have ample training resources, a custom translation model can be the ideal choice for your organization.
27+
Ultimately, if you need translations that reflect your industry's specific language and you have ample training resources, a custom translation model can be the ideal choice for your organization.
2828

29-
:::image type="content" source="media/how-to/for-beginners.png" alt-text="Screenshot illustrating the difference between custom and general models.":::
29+
:::image type="content" source="../media/how-to/for-beginners.png" alt-text="Screenshot illustrating the difference between custom and general models.":::
3030

3131
## What does training a custom translation model involve?
3232

@@ -76,15 +76,15 @@ Finding in-domain quality data is often a challenging task that varies based on
7676

7777
## What is a BLEU score?
7878

79-
BLEU (Bilingual Evaluation Understudy) is an algorithm for evaluating the precision or accuracy of text that is machine translated from one language to another. Custom Translation uses the BLEU metric as one way of conveying translation accuracy.
79+
BLEU (Bilingual Evaluation Understudy) is an algorithm for evaluating the precision or accuracy of text that is machine translated from one language to another. Custom translation uses the BLEU metric as one way of conveying translation accuracy.
8080

8181
A BLEU score is a number between zero and 100. A score of zero indicates a low quality translation where nothing in the translation matched the reference. A score of 100 indicates a perfect translation that is identical to the reference. It's not necessary to attain a score of 100 - a BLEU score between 40 and 60 indicates a high-quality translation.
8282

8383
[Read more](concepts/bleu-score.md?WT.mc_id=aiml-43548-heboelma)
8484

8585
## What happens if I don't submit tuning or testing data?
8686

87-
Tuning and test sentences are optimally representative of what you plan to translate in the future. If you don't submit any tuning or testing data, Custom Translation automatically excludes sentences from your training documents to use as tuning and test data.
87+
Tuning and test sentences are optimally representative of what you plan to translate in the future. If you don't submit any tuning or testing data, custom translation automatically excludes sentences from your training documents to use as tuning and test data.
8888

8989
| System-generated | Manual-selection |
9090
|---|---|
@@ -93,13 +93,13 @@ Tuning and test sentences are optimally representative of what you plan to trans
9393
| Easy to redo when you grow or shrink the domain. | Allows for more data and better domain coverage.|
9494
|Changes each training run.| Remains static over repeated training runs|
9595

96-
## How is training material processed by Custom Translation?
96+
## How is training material processed by custom translation?
9797

98-
To prepare for training, documents undergo a series of processing and filtering steps. Knowledge of the filtering process can help with understanding the sentence count displayed as well as the steps you can take to prepare training documents for training with Custom Translation. The filtering steps are as follows:
98+
To prepare for training, documents undergo a series of processing and filtering steps. Knowledge of the filtering process can help with understanding the sentence count displayed as well as the steps you can take to prepare training documents for training with custom translation. The filtering steps are as follows:
9999

100100
* ### Sentence alignment
101101

102-
If your document isn't in `XLIFF`, `XLSX`, `TMX`, or `ALIGN` format, Custom Translation 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 Translation tries to find the corresponding sentence in the target language. It uses document markup like embedded HTML tags to help with the alignment.
102+
If your document isn't in `XLIFF`, `XLSX`, `TMX`, or `ALIGN` format, custom translation 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 translation tries to find the corresponding sentence in the target language. It uses document markup like embedded HTML tags to help with the alignment.
103103

104104
If you see a large discrepancy between the number of sentences in the source and target documents, your source document can't 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.
105105

@@ -139,11 +139,11 @@ To prepare for training, documents undergo a series of processing and filtering
139139

140140
* ### Invalid characters
141141

142-
Custom Translation removes sentences that contain Unicode character U+FFFD. The character U+FFFD indicates a failed encoding conversion.
142+
custom translation removes sentences that contain Unicode character U+FFFD. The character U+FFFD indicates a failed encoding conversion.
143143

144144
* ### Invalid HTML tags
145145

146-
Custom Translation removes valid tags during training. Invalid tags cause unpredictable results and should be manually removed.
146+
custom translation removes valid tags during training. Invalid tags cause unpredictable results and should be manually removed.
147147

148148
## What steps should I take before uploading data?
149149

@@ -163,4 +163,4 @@ After your model is successfully trained, you can view the model's BLEU score an
163163
## Next steps
164164

165165
> [!div class="nextstepaction"]
166-
> [Try create project](../azure-ai-foundry/how-to-custom-translation-create-project.md)
166+
> [Try create project](../azure-ai-foundry/how-to/create-project.md)
Lines changed: 9 additions & 21 deletions
Original file line numberDiff line numberDiff line change
@@ -1,47 +1,35 @@
11
---
2-
title: "What is a BLEU score? - Custom Translation"
2+
title: Azure AI Foundry custom translation BLEU score
33
titleSuffix: Azure AI services
4-
description: BLEU is a measurement of the differences between machine translation and human-created reference translations of the same source sentence.
4+
description: The BLEU score measures the differences between machine translation and human-created reference translations of the same source sentence.
55
author: laujan
66
manager: nitinme
77
ms.service: azure-ai-translator
88
ms.topic: conceptual
9-
ms.date: 01/27/2025
9+
ms.date: 05/19/2025
1010
ms.author: lajanuar
1111
ms.custom: cogserv-non-critical-translator
12-
#Customer intent: As an Custom Translation user, I want to understand how BLEU score works so that I understand system test outcome better.
12+
#Customer intent: As an custom translation user, I want to understand how BLEU score works so that I understand system test outcome better.
1313
---
1414

15-
# What is a BLEU score?
15+
# Azure AI Foundry custom translation BLEU score
1616

1717
[BLEU (Bilingual Evaluation Understudy)](https://en.wikipedia.org/wiki/BLEU) is a measurement of the difference between an automatic translation and human-created reference translations of the same source sentence.
1818

1919
## Scoring process
2020

21-
The BLEU algorithm compares consecutive phrases of the automatic translation
22-
with the consecutive phrases it finds in the reference translation, and counts
23-
the number of matches, in a weighted fashion. These matches are position
24-
independent. A higher match degree indicates a higher degree of similarity with
25-
the reference translation, and higher score. Intelligibility and grammatical correctness aren't taken into account.
21+
The BLEU algorithm compares consecutive phrases of the automatic translation with the consecutive phrases it finds in the reference translation, and counts the number of matches, in a weighted fashion. These matches are position independent. A higher match degree indicates a higher degree of similarity with the reference translation, and higher score. Intelligibility and grammatical correctness aren't taken into account.
2622

2723
## How BLEU works?
2824

29-
The BLEU score's strength is that it correlates well with human judgment. BLEU averages out
30-
individual sentence judgment errors over a test corpus, rather than attempting
31-
to devise the exact human judgment for every sentence.
25+
The BLEU score's strength is that it correlates well with human judgment. BLEU averages out individual sentence judgment errors over a test corpus, rather than attempting to devise the exact human judgment for every sentence.
3226

33-
A more extensive discussion of BLEU scores is [here](https://youtu.be/-UqDljMymMg).
34-
35-
BLEU results depend strongly on the breadth of your domain; consistency of
36-
test, training and tuning data; and how much data you have
37-
available for training. If your models are trained within a narrow domain, and
38-
your training data is consistent with your test data, you can expect a high
39-
BLEU score.
27+
For a more extensive discussion of BLEU scores, *see* [Microsoft Translator Hub - Discussion of BLEU Score](https://youtu.be/-UqDljMymMg). BLEU results depend strongly on the breadth of your domain; consistency of test, training and tuning data; and how much data you have available for training. If your models are trained within a narrow domain, and your training data is consistent with your test data, you can expect a high BLEU score.
4028

4129
>[!NOTE]
4230
>A comparison between BLEU scores is only justifiable when BLEU results are compared with the same Test set, the same language pair, and the same MT engine. A BLEU score from a different test set is bound to be different.
4331
4432
## Next steps
4533

4634
> [!div class="nextstepaction"]
47-
> [BLEU score evaluation](../how-to-custom-translation-test-model.md)
35+
> [BLEU score evaluation](../how-to/test-model.md)
Lines changed: 9 additions & 9 deletions
Original file line numberDiff line numberDiff line change
@@ -1,23 +1,23 @@
11
---
2-
title: Translation Customization - Custom Translation
2+
title: Azure AI Foundry custom translations
33
titleSuffix: Azure AI services
4-
description: Use the Microsoft Translator Hub to build your own machine translation system using your preferred terminology and style.
4+
description: Build your own machine translation system using your preferred terminology and style.
55
#services: cognitive-services
66
author: laujan
77
manager: nitinme
88
ms.service: azure-ai-translator
99
ms.topic: conceptual
10-
ms.date: 01/28/2025
10+
ms.date: 05/19/2025
1111
ms.author: lajanuar
1212
---
1313

14-
# Customize your text translations
14+
# Azure AI Foundry custom translations
1515

16-
Custom Translation is a feature of the Azure AI Translator service. Custom Translation allows users to customize Azure AI Translator's advanced neural machine translation when translating text using Translator (version 3 only).
16+
Custom translation is a feature of the Azure AI Translator service. Azure AI Foundry custom translation allows users to customize Azure AI Translator's advanced neural machine translation when translating text using Translator (version 3 only).
1717

18-
The feature can also be used to customize speech translation when used with [Azure AI Speech](../../../speech-service/index.yml).
18+
The feature can also be used to customize speech translation when used with [Azure AI Speech](../../../../speech-service/index.yml).
1919

20-
## Custom Translation
20+
## Custom translation
2121

2222
With Custom Translator, you can build neural translation systems that understand the terminology used in your own business and industry. The customized translation system integrates into existing applications, workflows, and websites.
2323

@@ -31,9 +31,9 @@ The customized system is then available through a regular call to Translator usi
3131

3232
Given the appropriate type and amount of training data it isn't uncommon to expect gains between 5 and 10, or even more `BLEU` points on translation quality by using Custom Translator.
3333

34-
More details about the various levels of customization based on available data can be found in the [Custom Translation User Guide](../overview.md).
34+
More details about the various levels of customization based on available data can be found in the [Custom translation User Guide](../overview.md).
3535

3636
## Next steps
3737

3838
> [!div class="nextstepaction"]
39-
> [Set up a customized language system using Custom Translation](../overview.md)
39+
> [Set up a customized language system using custom translation](../overview.md)

0 commit comments

Comments
 (0)