Amazon Comprehend - Developer Guide

1 Amazon ComprehendDeveloper GuideAmazon Comprehend Developer GuideAmazon Comprehend : Developer GuideCopyright 2018 Amazon Web Services, Inc. and/or its affiliates. All rights 's trademarks and trade dress may not be used in connection with any product or service that is not Amazon 's, in any mannerthat is likely to cause confusion among customers, or in any manner that disparages or discredits Amazon . All other trademarks notowned by Amazon are the property of their respective owners, who may or may not be affiliated with, connected to, or sponsored Comprehend Developer GuideTable of ContentsWhat Is Amazon Comprehend ? .. 1 Topic Modeling .. 2 Are You a First-time User of Amazon Comprehend ? .. 2 How It Works .. 3 Dominant 5 Key Phrases .. 7 Syntax .. 8 Topic Modeling .. 10 Asynchronous Batch Processing .. 13 Prerequisites .. 13 Starting an Analysis Job .. 13 Monitoring Analysis 14 Getting Analysis Results.

2 14 Multiple Document Synchronous Processing .. 17 Single-Document Processing .. 19 Getting Started .. 20 Step 1: Set Up an Account .. 20 Sign Up for AWS .. 20 Create an IAM User .. 21 Next Step .. 21 Step 2: Set Up the AWS CLI .. 21 Next Step .. 22 Step 3: Getting Started Using the Console .. 22 Analyzing Documents Using the 22 Creating a Topic Modeling Job Using the Console .. 26 Step 4: Getting Started Using the API .. 30 Detecting the Dominant Language .. 30 Detecting Named Entities .. 32 Detecting Key Phrases .. 35 Detecting Sentiment .. 37 Detecting Syntax .. 39 Topic Modeling .. 43 Using the Batch 48 Authentication and Access Control .. 56 Access Control .. 57 Overview of Managing Access .. 57 Managing Access to Actions .. 57 Specifying Policy Elements: Actions, Effects, and Principals .. 58 Specifying Conditions in a Policy .. 59 Using Identity-Based Policies (IAM Policies) for Amazon Comprehend .. 59 Permissions Required to Use the Amazon Comprehend Console.

3 60 AWS Managed (Predefined) Policies for Amazon Comprehend .. 61 Role-Based Permissions Required for Asynchronous Operations .. 62 Customer Managed Policy Examples .. 63 Amazon Comprehend API Permissions Reference .. 64 Guidelines and 65 Supported Regions .. 65 Throttling .. 65 Overall Limits .. 65iiiAmazon Comprehend Developer GuideMultiple Document 65 Asynchronous Operations .. 66 Language Detection .. 66 Topic Modeling .. 66 API Reference .. 68 Actions .. 68 BatchDetectDominantLanguage .. 69 BatchDetectEntities .. 72 BatchDetectKeyPhrases .. 75 BatchDetectSentiment .. 78 BatchDetectSyntax .. 81 DescribeDominantLanguageDetectionJob .. 84 DescribeEntitiesDetectionJob .. 86 DescribeKeyPhrasesDetectionJob .. 88 DescribeSentimentDetectionJob .. 90 DescribeTopicsDetectionJob .. 92 DetectDominantLanguage .. 94 DetectEntities .. 97 DetectKeyPhrases .. 100 DetectSentiment .. 103 DetectSyntax .. 106 ListDominantLanguageDetectionJobs.

4 108 ListEntitiesDetectionJobs .. 111 ListKeyPhrasesDetectionJobs .. 114 ListSentimentDetectionJobs .. 117 ListTopicsDetectionJobs .. 120 StartDominantLanguageDetectionJob .. 123 StartEntitiesDetectionJob .. 126 StartKeyPhrasesDetectionJob .. 129 StartSentimentDetectionJob .. 132 StartTopicsDetectionJob .. 135 StopDominantLanguageDetectionJob .. 138 StopEntitiesDetectionJob .. 140 StopKeyPhrasesDetectionJob .. 142 StopSentimentDetectionJob .. 144 Data Types .. 145 BatchDetectDominantLanguageItemResult .. 147 BatchDetectEntitiesItemResult .. 148 BatchDetectKeyPhrasesItemResult .. 149 BatchDetectSentimentItemResult .. 150 BatchDetectSyntaxItemResult .. 151 BatchItemError .. 153 DominantLanguageDetectionJobFilter .. 154 DominantLanguageDetectionJobProperties .. 155 EntitiesDetectionJobFilter .. 157 EntitiesDetectionJobProperties .. 158 Entity .. 162 KeyPhrase .. 163 KeyPhrasesDetectionJobFilter .. 164 KeyPhrasesDetectionJobProperties.

5 167 PartOfSpeechTag .. 168 SentimentDetectionJobFilter .. 169 SentimentDetectionJobProperties .. 170 SentimentScore .. 172ivAmazon Comprehend Developer GuideSyntaxToken .. 173 TopicsDetectionJobFilter .. 174 TopicsDetectionJobProperties .. 175 Common Errors .. 176 Common Parameters .. 178 Document History .. 180vAmazon Comprehend Developer GuideTopic ModelingWhat Is Amazon Comprehend ? Amazon Comprehend uses natural language processing (NLP) to extract insights about the contentof documents. Amazon Comprehend processes any text file in UTF-8 format. It develops insights byrecognizing the entities, key phrases, language, sentiments, and other common elements in a Amazon Comprehend to create new products based on understanding the structure of example, using Amazon Comprehend you can search social networking feeds for mentions ofproducts or scan an entire document repository for key work with one document at a time to detect entities, key phrases, languages, and sentiments.

6 Eachdocument is processed separately. Some of the insights that Amazon Comprehend develops about adocument include: Entities Amazon Comprehend returns a list of entities, such as people, places, and locations,identified in a document. For more information, see Entities (p. 5). Key phrases Amazon Comprehend extracts key phrases that appear in a document. For example, adocument about a basketball game might return the names of the teams, the name of the venue, andthe final score. For more information, see Key Phrases (p. 6). Language Amazon Comprehend identifies the dominant language in a document. AmazonComprehend can identify 100 languages. For more information, see Dominant Language (p. 3). Sentiment Amazon Comprehend determines the emotional sentiment of a document. Sentiment canbe positive, neutral, negative, or mixed. For more information, see Sentiments (p. 7). Syntax Amazon Comprehend parses each word in your document and determines the part of speechfor the word.

7 For example, in the sentence "It is raining today is Seattle," "it" is identified as a pronoun,"raining" is identified as a verb, and "Seattle" is identified as a proper noun. For more information, seeSyntax (p. 8).Topic ModelingYou can also use Amazon Comprehend to examine a corpus of documents to find the common themescontained within the corpus. Amazon Comprehend examines the documents in the corpus and thenreturns the most prominent topics and the documents that are associated with each modeling is a asynchronous process, you submit a set of documents for processing and thenlater get the results when processing is complete. Amazon Comprehend does topic modeling on largedocument sets, for best results you should include at least 1,000 documents when you submit a topicmodeling job. For more information, see Topic Modeling (p. 10).ExamplesThe following examples show how you might use the Amazon Comprehend operations in 1: Find documents about a subjectFind the documents about a particular subject using Amazon Comprehend topic modeling.

8 Scan a set ofdocuments to determine the topics discussed, and to find the documents associated with each topic. Youcan specify the number of topics that Amazon Comprehend should return from the document Comprehend Developer GuideBenefitsExample 2: Find out how customers feel about your productsIf your company publishes a catalog, let Amazon Comprehend tell you what customers think of yourproducts. Send each customer comment to the DetectSentiment operation and it will tell you whethercustomers feel positive, negative, neutral, or mixed about a 3: Discover what matters to your customersUse Amazon Comprehend topic modeling to discover the topics that your customers are talking about onyour forums and message boards, then use entity detection to determine the people, places, and thingsthat they associate with the topic. Finally, use sentiment analysis to determine how your customers feelabout a of the benefits of using Amazon Comprehend include: Integrate powerful natural language processing into your apps Amazon Comprehend removesthe complexity of building text analysis capabilities into your applications by making powerful andaccurate natural language processing available with a simple API.

9 You don't need textual analysisexpertise to take advantage of the insights that Amazon Comprehend produces. Deep learning based natural language processing Amazon Comprehend uses deep learningtechnology to accurately analyze text. Our models are constantly trained with new data acrossmultiple domains to improve accuracy. Scalable natural language processing Amazon Comprehend enables you to analyze millions ofdocuments so that you can discover the insights that they contain. Integrate with other AWS services Amazon Comprehend is designed to work seamlessly with otherAWS services like Amazon S3 and AWS Lambda. Store your documents in Amazon S3, or analyze real-time data with Kinesis Data Firehose. Support for AWS Identity and Access Management (IAM) makesit easy to securely control access to Amazon Comprehend operations. Using IAM, you can create andmanage AWS users and groups to grant the appropriate access to your developers and end users.

10 Low cost With Amazon Comprehend , you only pay for the documents that you analyze. There are nominimum fees or upfront You a First-time User of Amazon Comprehend ?If you are a first-time user of Amazon Comprehend , we recommend that you read the following sectionsin order:1. How It Works (p. 3) This section introduces Amazon Comprehend Getting Started with Amazon Comprehend (p. 20) In this section, you set up your account andtest Amazon API Reference (p. 68) In this section you'll find reference documentation for AmazonComprehend Comprehend Developer GuideDominant LanguageHow It WorksAmazon Comprehend uses a pre-trained model to examine a document or set of documents to gatherinsights about the document set. The model is continuously trained on a large body of text so that thereis no need for you to provide training data. Except for the DetectDominantLanguage (p. 94) operation, Amazon Comprehend can examine documents in these languages: English SpanishAmazon Comprehend provides the following operations: Single-Document Processing (p.)