Skip to content

Commit 2053b74

Browse files
committed
acrolinx pass
1 parent 52d158f commit 2053b74

File tree

6 files changed

+16
-16
lines changed

6 files changed

+16
-16
lines changed

articles/ai-services/language-service/custom-text-classification/concepts/evaluation-metrics.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -26,7 +26,7 @@ Model evaluation is triggered automatically after training is completed successf
2626

2727
`Recall = #True_Positive / (#True_Positive + #False_Negatives)`
2828

29-
* **F1 score**: The F1 score is a function of Precision and Recall. It's needed when you seek a balance between Precision and Recall.
29+
* **F1 score**: The F1 score is a function of precision and recall. It's needed when you seek a balance between Precision and Recall.
3030

3131
`F1 Score = 2 * Precision * Recall / (Precision + Recall)` <br>
3232

@@ -89,7 +89,7 @@ The below sections use the following example dataset:
8989
**F1 Score** = `2 * Precision * Recall / (Precision + Recall) = (2 * 0.8 * 0.67) / (0.8 + 0.67) = 0.73`
9090

9191
> [!NOTE]
92-
> For single-label classification models, the count of false negatives and false positives are always equal. Custom single-label classification models always predict one class for each document. If the prediction is not correct, FP count of the predicted class increases by one and FN of the actual class increases by one, overall count of FP and FN for the model will always be equal. This is not the case for multi-label classification, because failing to predict one of the classes of a document is counted as a false negative.
92+
> For single-label classification models, the number of false negatives and false positives are always equal. Custom single-label classification models always predict one class for each document. If the prediction is not correct, FP count of the predicted class increases by one and FN of the actual class increases by one, overall number of FP and FN for the model will always be equal. This is not the case for multi-label classification, because failing to predict one of the classes of a document is counted as a false negative.
9393
## Interpreting class-level evaluation metrics
9494

9595
So what does it actually mean to have a high precision or a high recall for a certain class?

articles/ai-services/language-service/language-detection/language-support.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -6,7 +6,7 @@ author: jboback
66
manager: nitinme
77
ms.service: azure-ai-language
88
ms.topic: conceptual
9-
ms.date: 11/21/2024
9+
ms.date: 06/06/2025
1010
ms.author: jboback
1111
ms.custom: language-service-language-detection, ignite-2024
1212
---

articles/ai-services/language-service/orchestration-workflow/quickstart.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -6,7 +6,7 @@ author: jboback
66
manager: nitinme
77
ms.service: azure-ai-language
88
ms.topic: quickstart
9-
ms.date: 11/21/2024
9+
ms.date: 06/06/2025
1010
ms.author: jboback
1111
ms.custom: language-service-clu, mode-other
1212
zone_pivot_groups: usage-custom-language-features

articles/ai-services/language-service/question-answering/concepts/best-practices.md

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -5,7 +5,7 @@ ms.service: azure-ai-language
55
author: jboback
66
ms.author: jboback
77
ms.topic: conceptual
8-
ms.date: 11/21/2024
8+
ms.date: 06/06/2025
99
ms.custom: language-service-question-answering
1010
---
1111

@@ -55,7 +55,7 @@ Users can add as many alternate questions as they want, but only first 5 will be
5555

5656
Semantic understanding in custom question answering should be able to take care of similar alternate questions.
5757

58-
The return on investment will start diminishing once you exceed 10 questions. Even if you’re adding more than 10 alternate questions, try to make the initial 10 questions as semantically dissimilar as possible so that all kinds of intents for the answer are captured by these 10 questions. For the project at the beginning of this section, in question answer pair #1, adding alternate questions such as “How can I buy a car”, “I wanna buy a car” aren’t required. Whereas adding alternate questions such as “How to purchase a car”, “What are the options of buying a vehicle” can be useful.
58+
The return on investment will start diminishing once you exceed 10 questions. Even if you’re adding more than 10 alternate questions, try to make the initial 10 questions as semantically dissimilar as possible so that all kinds of intents for the answer are captured by these 10 questions. For the project at the beginning of this section, in question answer pair #1, adding alternate questions such as “How can I buy a car,” “I wanna buy a car” aren’t required. Whereas adding alternate questions such as “How to purchase a car,” “What are the options of buying a vehicle” can be useful.
5959

6060
### When to add synonyms to a project?
6161

@@ -67,11 +67,11 @@ For better relevance, you need to provide a list of acronyms that the end user i
6767
* `ID` – Identification
6868
* `ETA` – Estimated time of Arrival
6969

70-
Other than acronyms, if you think your words are similar in context of a particular domain and generic language models won’t consider them similar, it’s better to add them as synonyms. For instance, if an auto company producing a car model X receives queries such as “my car’s audio isn’t working” and the project has questions on “fixing audio for car X”, then we need to add ‘X’ and ‘car’ as synonyms.
70+
Other than acronyms, if you think your words are similar in context of a particular domain and generic language models won’t consider them similar, it’s better to add them as synonyms. For instance, if an auto company producing a car model X receives queries such as “my car’s audio isn’t working” and the project has questions on “fixing audio for car X,” then we need to add ‘X’ and ‘car’ as synonyms.
7171

7272
The transformer-based model already takes care of most of the common synonym cases, for example: `Purchase – Buy`, `Sell - Auction`, `Price – Value`. For another example, consider the following question answer pair: Q: “What is the price of Microsoft Stock?” A: “$200”.
7373

74-
If we receive user queries like “Microsoft stock value”,” Microsoft share value”, “Microsoft stock worth”, “Microsoft share worth”, “stock value”, etc., you should be able to get the correct answer even though these queries have words like "share", "value", and "worth", which aren’t originally present in the project.
74+
If we receive user queries like “Microsoft stock value,”” Microsoft share value,” “Microsoft stock worth,” “Microsoft share worth,” “stock value,” etc., you should be able to get the correct answer even though these queries have words like "share", "value", and "worth", which aren’t originally present in the project.
7575

7676
Special characters are not allowed in synonyms.
7777

articles/ai-services/language-service/question-answering/how-to/network-isolation.md

Lines changed: 7 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -5,13 +5,13 @@ ms.service: azure-ai-language
55
ms.topic: how-to
66
author: jboback
77
ms.author: jboback
8-
ms.date: 11/21/2024
8+
ms.date: 06/06/2025
99
ms.custom: language-service-question-answering
1010
---
1111

1212
# Network isolation and private endpoints
1313

14-
The steps below describe how to restrict public access to custom question answering resources as well as how to enable Azure Private Link. Protect an AI Foundry resource from public access by [configuring the virtual network](../../../cognitive-services-virtual-networks.md?tabs=portal).
14+
The following steps describe how to restrict public access to custom question answering resources and how to enable Azure Private Link. Protect an AI Foundry resource from public access by [configuring the virtual network](../../../cognitive-services-virtual-networks.md?tabs=portal).
1515

1616
## Private Endpoints
1717

@@ -21,14 +21,14 @@ Private endpoints are provided by [Azure Private Link](/azure/private-link/priva
2121

2222
## Steps to enable private endpoint
2323

24-
1. Assign *Contributer* role to language resource (Depending on the context this may appear as a Text Analytics resource) in the Azure Search Service instance. This operation requires *Owner* access to the subscription. Go to Identity tab in the service resource to get the identity.
24+
1. Assign the *contributer* role to the resource in the Azure Search Service instance. This operation requires *Owner* access to the subscription. Go to Identity tab in the service resource to get the identity.
2525

2626
> [!div class="mx-imgBorder"]
2727
> ![Text Analytics Identity](../../../QnAMaker/media/qnamaker-reference-private-endpoints/private-endpoints-identity.png)
2828
29-
2. Add the above identity as *Contributer* by going to Azure Search Service IAM tab.
29+
2. Add the identity as a *contributer* by going to Azure Search Service access control tab.
3030

31-
![Managed service IAM](../../../QnAMaker/media/qnamaker-reference-private-endpoints/private-endpoint-access-control.png)
31+
![Managed service](../../../QnAMaker/media/qnamaker-reference-private-endpoints/private-endpoint-access-control.png)
3232

3333
3. Select on *Add role assignments*, add the identity and select *Save*.
3434

@@ -38,7 +38,7 @@ Private endpoints are provided by [Azure Private Link](/azure/private-link/priva
3838

3939
![Managed Azure search networking](../../../QnAMaker/media/qnamaker-reference-private-endpoints/private-endpoint-networking.png)
4040

41-
5. Go to *Networking* tab of language resource and under the *Allow access from*, select the *Selected Networks and private endpoints* option and select *save*.
41+
5. Go to the **Networking** tab of the resource. Under the **Allow access from** section, select the **Selected Networks and private endpoints** option and select **save**.
4242

4343
> [!div class="mx-imgBorder"]
4444
> ![Text Analytics networking](../../../QnAMaker/media/qnamaker-reference-private-endpoints/private-endpoint-networking-custom-qna.png)
@@ -56,7 +56,7 @@ This will establish a private endpoint connection between language resource and
5656

5757
Follow the steps below to restrict public access to custom question answering language resources. Protect an AI Foundry resource from public access by [configuring the virtual network](../../../cognitive-services-virtual-networks.md?tabs=portal).
5858

59-
After restricting access to an AI Foundry resource based on VNet, To browse projects on Language Studio from your on-premises network or your local browser.
59+
After you restrict access to an AI Foundry resource based on virtual network, to browse projects on Language Studio from your on-premises network or your local browser.
6060
- Grant access to [on-premises network](../../../cognitive-services-virtual-networks.md?tabs=portal#configure-access-from-on-premises-networks).
6161
- Grant access to your [local browser/machine](../../../cognitive-services-virtual-networks.md?tabs=portal#managing-ip-network-rules).
6262
- Add the **public IP address of the machine under the Firewall** section of the **Networking** tab. By default `portal.azure.com` shows the current browsing machine's public IP (select this entry) and then select **Save**.

articles/ai-services/language-service/sentiment-opinion-mining/how-to/use-containers.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -6,7 +6,7 @@ author: jboback
66
manager: nitinme
77
ms.service: azure-ai-language
88
ms.topic: how-to
9-
ms.date: 11/21/2024
9+
ms.date: 06/06/2025
1010
ms.author: jboback
1111
ms.custom: language-service-sentiment-opinion-mining
1212
keywords: on-premises, Docker, container, sentiment analysis, natural language processing

0 commit comments

Comments
 (0)