Text Analytics
Welcome to the Text Analytics Forum
Categories
API – Any ideas or feedback pertaining to features or enhancements to Text Analytics API.
Documentation – Any ideas or suggestions for the API Reference or Documentation.
Language Support – Submit a request to have a particular language supported.
Samples & SDK Request – Let us know if you would like to see a Code sample or SDK provided.
-
What is the definition of transaction in Text Analytics API
After several calls to Text Analytics API, I noticed that the amount of transactions > the amount of calls. So how is transaction defined?
2 votes -
Intermittently unavailable
For the past two months, when I have tried to call the APIs, I have not been able to access the resource. When I check the resource health in Azure, it's unavailable. This happened with the text analytics service in both of our Azure accounts. Last month this seems to have resolved on it's own and we never heard back from Azure about our support request. I tend to go in to run a bunch of transactions in the final days before our monthly allotment resets, and this really throws a wrench in that!
1 voteHello,
I know it has been some time but you can always check the status of your service here: https://azure.microsoft.com/en-us/status/.
Thanks,
Luke -
incorrect language detection results
String "Congrats !! Congrats !!" is detected as Tagalog instead of English.
Example:
POST https://westus.api.cognitive.microsoft.com/text/analytics/v2.0/languages HTTP/1.1
Host: westus.api.cognitive.microsoft.com
Content-Type: application/json
Ocp-Apim-Subscription-Key: ••••••••••••••••••••••••••••••••{
"documents": [{
"id": "1",
"text": "Congrats !! Congrats !!"
}]
}
Transfer-Encoding: chunked
x-ms-transaction-count: 1
x-aml-ta-request-id: ceea3fb2-ad0a-4b14-ae8e-54c584ab86e5
X-Content-Type-Options: nosniff
apim-request-id: c60db805-a194-4cd5-89af-c68d6ef87ed8
Strict-Transport-Security: max-age=31536000; includeSubDomains; preload
Date: Mon, 11 Jun 2018 20:53:11 GMT
Content-Type: application/json; charset=utf-8{
"documents": [{"id": "1",
"detectedLanguages": [{
"name": "Filipino",
"iso6391Name": "tl",
"score": 1.0
}]}],
"errors": []
}2 votes -
Classify the type of entities (people, location, business, dates)
I enjoyed testing the text analytics API, however I noticed that while the service detects entities, it doesn't appear to classify them. For example, I would expect the service to identify a person from a business or street name. Similarly, can it detect an address such as 123 Elm Street, City, State, Zip. I anticipate that this would be a valuable add-on.
6 votes -
Add Linguistic Analysis features (part of speech tagging, tokenizing, etc)
Add features to Text Analytics to identify the concepts and actions in your text with part-of-speech tagging, and find phrases and concepts using natural language parsers and tokenizers.
1 vote -
Add Wikidata Entity Linking References
The entity linking feature should include or at least allow the option of Wikidata references. Wikidata will allow for much more programmable context vs Wikipedia.
So for example, if the entity "Seattle" was found, we should have a reference to this link from wikidata. "https://www.wikidata.org/wiki/Q5083" which has a ton of contextual data for programmers to access. Such as this is a city, in the state of WA as well as who the mayor is, etc, etc...
1 voteHello,
This feature is in preview. Please see: https://docs.microsoft.com/en-us/azure/cognitive-services/text-analytics/overview#entity-recognition-preview
Thanks,
Luke -
Telugu
Looking forward to see support for Telugu and Hindi.. I'll be morethan happy to volunteer.
1 vote -
Lang detection score needs guidance and probably enhancement
The lang detection API provides a score. The only details are that 1.0 indicates the highest level of confidence, and that a lower score will be returned in mixed language situations. Here are a couple of cases which don't seem to agree:
The example in the docs, leaving the english and spanish, but removing the french, is still mixed:
Hello, I would like to take a class at your University. ¿Se ofrecen clases en español? Es mi primera lengua y más fácil para escribir.
--> returns Spanish, score 1
Hey, that's life. C'est la vie!
--> returns French, score 1
…
2 votes -
Can I teach key-phase and sentiment ?
There are many simple rule key-phases that expression feelings in Japanese.
ex.
にこにこ +(positive)
じめじめ -(negative)
などなど +- (neutral)I want to teach that's words cognitive engine.
Can I teach key-phase and sentiment?2 votes -
Allow addition of custom vocabulary to improve keyword detection
For example the keywords "Intramolecular", "ionic", "covalent", "intermolecular" are not currently recognized.
8 votes -
Entity extraction for fixed format text (ticket number, phone number..etc)
Extract entities from text. example return a Jira task number "TES-10" usually they have a set of rules (ProjectKey-Number) but currently Text analytics is not able to recognize the full entity (returns ProjectKey only).
6 votes -
Sentiment analysis in portuguese Brazil
I think that sentiment analysis in portuguese Brazil it would be great.
There are so much professionals in Brazil that would like to do sentiment analysis in portuguese-Brazil.Thanks so much
62 votes -
please add support for Arabic
Having support for Arabic language will help create amazing user experiences across the Arab speaking world and provide amazing insights into their texts.... Please add this
14 votes -
Where did the Topic Detection API go?
I no longer see the topic detection API as part of the Text Analytics services? Is it still available to use? This worked quite well
2 votesTopic detection was deprecated before going to General Availability.
https://gallery.cortanaintelligence.com/Experiment/Topic-Detection has a Azure Machine Learning Studio experiment you could use to continue to support this scenario.
Since it is an experiment, you could modify it to meet your needs.
Thanks!
Luis Cabrera
Text Analytics PM -
Support Portuguese language for key-phrases
Please support Portuguese language for key-phrase extraction
3 votesDone.
Luis Cabrera
Text Analytics PM -
Text analysis - Provide rewards and a way for users to provide feedback to service response so that it can learn(Machine Learning).
While testing the sentences, it would be great to have users feedback whether the sentence and analysis makes sense or they feel the result has some issue.
Get survey details such as emotion, positive and negative scale, keywords and all
6 votes -
The keywords detection and contextual awareness should get better
Below statement is classified as 91%(positive) but the statement is highly negative
please provide email address or higher managements so we can contact them directly - as customer support is just lying - false promising on my refund
1 voteI am resolving this one since this is an ongoing process that we’ll never complete…
-
please support Indonesia language for text analiytics
I hope microsoft support this language, because indonesia have big population so it'll be usefull for text or spech analytic
2 votes -
Please add Ukrainian language support
Please add Ukrainian language support, thank you in advance.
16 votes -
Text Analytics for Czech
Please add Czech language support, thank you in advance.
16 votes
- Don't see your idea?