Brainscape's Knowledge GenomeTM

Browse over 1 million classes created by top students, professors, publishers, and experts.


See full index

AI-900 > NLP > Flashcards

NLP Flashcards

1
Q

What NLP services does Azure provide?

A

Text Analytics
Translator
Speech
Language Understanding Intelligent Service (LUIS)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What would you use Translator Text for?

A

Automatically translating spoken or written word between languages.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What would you use LUIS for?

A

Interpreting commands and determining appropriate actions.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What is Text Analytics?

A

A cloud-based service that provides advanced natural language processing over raw text for sentiment analysis, key phrase extraction, named entity recognition and language detection.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

What would you use Text Analytics for?

A

Analysing and interpreting text in documents, email messages, and other sources.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

What is frequency analysis?

A

Counting how often each word appears in text.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What is an N-gram?

A

A contiguous sequence of n items from a given sample of text or speech.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

What is an entity in Text Analytics?

A

People, places, organisations or everyday items like dates, times, quantities, and so on.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What does the language capability of Text Analytics detect for each document submitted to it?

A

The language (e.g. ‘English’)
The ISO 6391 code (e.g. ‘en’)
A score indicating the level of confidence in the language detection.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

What happens if a text with a mix of languages is submitted to Text Analytics service?

A

The service will focus on the predominant language in the text, and may return a confidence score less than 1.0

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

What could happen if you submitted ambiguous content to the Text Analytics service?

A

The service would return the language name and the language identifier as unknown and a score of NaN. (not a number)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

What would you use the language detection capability of Text Analytics for?

A

To identify the language a text is written in.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

What would you use the sentiment analysis capability of Text Analytics for?

A

Evaluating text to return sentiment scores and labels for each sentence.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

What is the range of the sentiment score?

A

0 - 1

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

What is a positive sentiment score?

A

Values close to 1.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

What is a negative sentiment score?

A

Values close to 0.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

What is a neutral or indeterminate sentiment score?

A

0.5

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

What could cause an indeterminate sentiment score?

A

A sentence without structure (like a list of words), or using the wrong language code. (e.g. telling the service a document is en(glish) but its actually fr(ench))

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

What would you use the key phrase extraction capability of Text Analytics for?

A

Identifying the main talking points of a document(s).

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

What would you use the entity recognition capability of Text Analytics for?

A

Getting a list of entities from a piece of text. The service can also provide links to more information about that entity on the web.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

What is Entity Linking?

A

The ability to disambiguate entities by linking to a specific reference. (Wikipedia)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
22
Q

What is Speech?

A

The unification of speech-to-text, text-to-speech, and speech-translation into a single Azure subscription.

23
Q

What would you use Speech for?

A

Interpreting spoken language, and synthesizing speech responses.

24
Q

What is speech-to-text?

A

An API that performs real-time or batch transcription of audio into a text format.

25
Q

What is text-to-speech?

A

An API that enables you to convert text input to audible speech, which can either be played directly through computer speakers or written to an audio file.

26
Q

What model is used by the speech-to-text API?

A

The Universal Language Model trained by Microsoft using Microsoft owned data, and is deployed to Microsoft Azure.

27
Q

What is the speech-to-text model optimised for?

A

Dictation and conversation.

28
Q

Can you use your own models for speech-to-text?

A

Yes, you can create and train your own custom models including acoustics, language, and pronunciation if the pre-built models from Microsoft are insufficient for your use case.

29
Q

What is needed in order for real-time transcription (real-time speech-to-text) to work?

A

An application has to be listening to incoming audio from a microphone, or other audio input source such as an audio file.

30
Q

How should batch transcription (batch speech-to-text) jobs be run?

A

Asynchronously as the batch jobs are scheduled on a best-effort basis. Normally, jobs start within minutes of the request, but there’s no estimate for when a job changes into the running state.

31
Q

How would you personalised your speech synthesis solution?

A

By specifying the voice to be used to vocalise the text.

32
Q

What voices are available with text-to-speech?

A

Multiple pre-defined voices with support for multiple languages and regional pronunciation, including standard voices as well as neural voices.

Additionally, you can develop custom voices for use with the service.

33
Q

What is a neural voice?

A

A voice that leverages neural networks to overcome common limitations in speech synthesis with regards to intonation, resulting in a more natural sounding voice.

34
Q

True or false: Speech-to text and text-to-speech only supports English?

A

False; They support a variety of languages.

35
Q

What is speech recognition?

A

The ability to detect and interpret spoken input.

36
Q

What is speech synthesis?

A

The ability to generate spoken output.

37
Q

What is Language Understanding (LUIS)?

A

A cloud-based conversational AI service that applied custom machine-learning intelligence to a user’s conversational, natural language text to predict overall meaning, and pull out relevant, detailed information.

38
Q

How can you access Language Understanding?

A

Through its web portal, APIs, and SDK client libraries.

39
Q

What are Language Understanding’s 3 core concepts?

A

Utterances, Intents, and Entities.

40
Q

What is an utterance?

A

An example of something a user might say, and which an application must interpret.

41
Q

What is an entity?

A

An item to which an utterance refers.

42
Q

What is an intent?

A

The goal expressed in a user’s utterance.

43
Q

What is the None intent?

A

A fall-back for providing a generic response to users when their requests don’t match any other intent.

It is a required intent that can’t be deleted or renamed.

44
Q

What are the 2 types of Language Understanding service?

A

Authoring and prediction.

45
Q

What are the three choices when creating a Language Understanding resource?

A

Authoring, prediction or both.

46
Q

What happens if you choose both when creating a Language Understanding resource?

A

Two resources will be made, a prediction resource and an authoring resource.

47
Q

What is the best practise for using Language Understanding?

A

Use the portal for authoring and the SDK for runtime predictions.

48
Q

What are the 4 types of entity?

A

Machine-Learned

List

RegEx

Pattern.any

49
Q

What is a Machine-Learned entity?

A

Entities that are learned by your model during training from context in the sample utterances you provide.

50
Q

What is a List entity?

A

Entities that are defined as a hierarchy of lists and sublists.

51
Q

What is a RegEx entity?

A

Entities that are defined as a regular expression that describes a pattern.

52
Q

What is a Pattern,any entity?

A

Entities that are used with patterns to define complex entities that may be hard to extract from sample utterances.

53
Q

What is training in Language Understanding?

A

The process of using your sample utterances to teach your model to match natural language expressions that a user might say to probable intents and entities.

AI-900 (7 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2024 Bold Learning Solutions. Terms and Conditions