AWS Comprehend

AWS Comprehend (NLP Tasks)

  • About - Amazon Comprehend uses natural language processing (NLP) to extract insights about the content of documents. It develops insights by recognizing the entities, key phrases, language, sentiments, and other common elements in a document. Use Amazon Comprehend to create new products based on understanding the structure of documents. For example, using Amazon Comprehend you can search social networking feeds for mentions of products or scan an entire document repository for key phrases.
  • Languages - Amazon Comprehend (except the detect dominant language feature) supports the following languages: German, English, Spanish, Italian, Portuguese, French, Japanese, Korean, Hindi, Arabic, Chinese (simplified),Chinese (traditional) here.
  • Features -
    • Custom Entity Recognition - Custom Entity Recognition allows you to customize Amazon Comprehend to identify terms that are specific to your domain. Using AutoML, Comprehend will learn from a small set of examples (for example, a list of policy numbers, claim numbers, or SSN), and then train a private, custom model to recognize these terms such as claim numbers in any other block of text within PDFs, plain text, or Microsoft Word documents – no machine learning required. Refer to this documentation page for more details. Example: In this example, an insurance company would like to analyze text documents for entities specific to their business, policy numbers.
    • Custom Classification - The Custom Classification API enables you to easily build custom text classification models using your business-specific labels without learning ML. For example, your customer support organization can use Custom Classification to automatically categorize inbound requests by problem type based on how the customer has described the issue.  With your custom model, it is easy to moderate website comments, triage customer feedback, and organize workgroup documents. Refer to this documentation page for more details. Example: Let’s say you want to organize your customer support feedback at an airline company. You want to organize each piece of feedback into Account Questions, Ticket Refunds and Flight Complaints. To train the service, you create a CSV file that contains example text from each issue, and label each sample with one of the three labels that applies. The service will automatically train a custom model on your behalf. To use your model to analyze all of the calls the next day, you submit each text file to the service and receive the labeled results along with a confidence of the label match.
    • Entity Recognition - The Entity Recognition API returns the named entities ("People," "Places," "Locations," etc.) that are automatically categorized based on the provided text. Refer to this documentation page for more details. Example: In this example, we are looking at the description of a company. The API identifies entities like Organization, Date, Location, and returns a confidence score.
    • Sentiment Analysis - The Sentiment Analysis API returns the overall sentiment of a text (Positive, Negative, Neutral, or Mixed). Refer to this documentation page for more details. Example: In this example, a customer is posting his feedback on a pair of shoes. The API identifies the sentiment expressed by the customer along with a confidence score.
    • Targeted Sentiment - Targeted Sentiment provides more granular sentiment insights by identifying the sentiment (positive, negative, neutral, or mixed) towards entities within text. Refer to this documentation page for more details. Example: In this example, a restaurant is reviewing a customer review to understand where they can improve their business.
    • PII Identification and Redaction - Use Amazon Comprehend ML capabilities to detect and redact personally identifiable information (PII) in customer emails, support tickets, product reviews, social media, and more. No ML experience required. For example, you can analyze support tickets and knowledge articles to detect PII entities and redact the text before you index the documents in the search solution. After that, search solutions are free of PII entities in documents. Redacting PII entities helps you protect privacy and comply with local laws and regulations. Refer to this documentation page for more details. Example: In this example, a customer is wants to redact personal and financial data from a bank statement. The PII redaction API will identify and redact PII along with a confidence score.
    • Keyphrase Extraction - The Keyphrase Extraction API returns the key phrases or talking points and a confidence score to support that this is a key phrase. Refer to this documentation page for more details. Example: In this example, a customer is comparing a DSLR camera to an instant film camera. The API extracts key phrases and returns a confidence score about the results.
    • Events Detection - Comprehend Events lets you extract the event structure from a document, distilling pages of text down to easily processed data for consumption by your AI applications or graph visualization tools. This API allows you to answer who-what-when-where questions over large document sets, at scale and without prior NLP experience. Use Comprehend Events to extract granular details about real-world events and associated entities expressed in unstructured text. Refer to this documentation page for more details.
    • Language Detection The Language Detection API automatically identifies text written in over 100 languages and returns the dominant language with a confidence score to support that a language is dominant. Refer to this documentation page for more details. Example: In this example, the API parses the text and is able to identify the dominant language in the text as Italian along with a confidence score.
    • Syntax Analysis The Amazon Comprehend Syntax API enables customers to analyze text using tokenization and Parts of Speech (PoS), and identify word boundaries and labels like nouns and adjectives within the text. Refer to this documentation page for more details. Example: In this example we will be analyzing a short document using the Comprehend Syntax API. The Syntax API tokenizes (defines word boundaries) text and labels each word with its associated part of speech e.g. noun ****and verb. In addition to noting begin and ending offset (so you know where the word is within the text), we also provide a confidence score.
    • Topic Modeling - Topic Modeling identifies relevant terms or topics from a collection of documents stored in Amazon S3. It will identify the most common topics in the collection and organize them in groups and then map which documents belong to which topic. Refer to this documentation page for more details.
    • Pricing -
      • Custom Comprehend Custom Entities & Classification For asynchronous entity recognition on PDF*, Word, and plain text documents $0.0005 PER UNIT. $3 PER HOUR FOR MODEL TRAINING $0.50 PER MONTH FOR MODEL MANAGEMENT to extract text from scanned PDF documents Amazon Textract Detect Document Text API is called.
      • Topic Modeling $1.00 (FLAT RATE) PER JOB For the first 100MB $0.004 PER MB For every MB above 100MB You are charged based on the total size of documents processed per topic modeling job. The first 100 MB is charged a flat rate. Above 100 MB, you are charged per MB.