Machine Learning | Amazon Comprehend Flashcards
What is Natural Language Processing?
General
Amazon Comprehend | Machine Learning
Natural Language Processing (NLP) is a way for computers to analyze, understand, and derive meaning from textual information in a smart and useful way. By utilizing NLP, you can extract important phrases, sentiment, key entities such as brand, date, location, person, etc., and the language of the text.
What is Amazon Comprehend?
General
Amazon Comprehend | Machine Learning
Amazon Comprehend is a natural language processing (NLP) service that uses machine learning to find meaning and insights in text.
What can I do with Amazon Comprehend?
General
Amazon Comprehend | Machine Learning
You can use Amazon Comprehend to identify the language of the text, extract key phrases, places, people, brands, or events, understand sentiment about products or services, and identify the main topics from a library of documents. The source of this text could be web pages, social media feeds, emails, or articles. You can also feed Amazon Comprehend a set of text documents, and it will identify topics (or group of words) that best represent the information in the collection. The output from Amazon Comprehend can be used to understand customer feedback, provide a better search experience through search filters, and uses topics to categorize documents.
How do I get started with Amazon Comprehend?
General
Amazon Comprehend | Machine Learning
You can get started with Amazon Comprehend from the AWS console. Your free tier for 12 months starts from the time you submit your first request. See product documentation on how to use Amazon Comprehend APIs in your application.
What are the most common use cases of Amazon Comprehend?
General
Amazon Comprehend | Machine Learning
The most common use cases include:
Voice of customer analytics: You can gauge whether customer sentiment is positive, neutral, negative, or mixed based on the feedback you receive via support calls, emails, social media, and other online channels.
Semantic search: You can use Amazon Comprehend to provide a better search experience by enabling your search engine to index key phrases, entities, and sentiment. This enables you to focus the search on the intent and the context of the articles instead of basic keywords.
Knowledge management and discovery: You can analyze a collection of documents and automatically organize them by topic. You can then use the topics to personalize content for your customers.
Do I have to be a natural language processing expert to use Amazon Comprehend?
General
Amazon Comprehend | Machine Learning
No, you don’t need NLP expertise to use Amazon Comprehend. You only need to call Amazon Comprehend’s API, and the service will handle the machine learning required to extract the relevant data from the text.
Is Amazon Comprehend a managed service?
General
Amazon Comprehend | Machine Learning
Amazon Comprehend is a fully managed and continuously trained service, so you don’t have to manage the scaling of resources, maintenance of code, or maintaining the training data.
Does Amazon Comprehend learn over time?
General
Amazon Comprehend | Machine Learning
Yes, Amazon Comprehend uses machine learning is continuously being trained to make it better for your use cases.
In which AWS regions in Amazon Comprehend available?
General
Amazon Comprehend | Machine Learning
For a list of the supported Amazon Comprehend AWS regions, please visit the AWS Region Table for all AWS global infrastructure. Also for more information, see Regions and Endpoints in the AWS General Reference.
What security measures does Amazon Comprehend have?
Usage
Amazon Comprehend | Machine Learning
Requests to the Amazon Comprehend API and console are made over a secure (SSL) connection. You can use AWS Identity and Access Management (AWS IAM) to control which IAM users have access to specific Amazon Comprehend actions and resources.
Where do I store my data?
Usage
Amazon Comprehend | Machine Learning
You can use user Amazon Comprehend to read your data from Amazon S3. You can also write the results from Amazon Comprehend to a storage service, database, or data warehouse.
How do I know if the service can process my data?
Usage
Amazon Comprehend | Machine Learning
For text analysis APIs, you will receive an HTTP status code of 200 indicating successful processing. If your data can’t be processed or exceeds service limits, you will get an appropriate HTTP error code.
How do I know if Amazon Comprehend is giving accurate results?
Usage
Amazon Comprehend | Machine Learning
The service will return a confidence score for each result. Low confidence scores mean that the service’s confidence is low that it is correct. Conversely, if the service is highly confident, the score will be closer to 1.
Can I import or use my own NLP model with Amazon Comprehend?
Pricing
Amazon Comprehend | Machine Learning
No. At the current time, Comprehend does not support custom models.
How is Amazon Comprehend priced?
Data privacy
Amazon Comprehend | Machine Learning
Refer to the Amazon Comprehend pricing page to learn more about pricing tiers and discounts.