{"id":2024,"date":"2022-03-25T18:45:00","date_gmt":"2022-03-25T18:45:00","guid":{"rendered":"https:\/\/salarydistribution.com\/machine-learning\/2022\/03\/25\/improve-search-accuracy-with-spell-checker-in-amazon-kendra\/"},"modified":"2022-03-25T18:45:00","modified_gmt":"2022-03-25T18:45:00","slug":"improve-search-accuracy-with-spell-checker-in-amazon-kendra","status":"publish","type":"post","link":"https:\/\/salarydistribution.com\/machine-learning\/2022\/03\/25\/improve-search-accuracy-with-spell-checker-in-amazon-kendra\/","title":{"rendered":"Improve search accuracy with Spell Checker in Amazon Kendra"},"content":{"rendered":"
\n

Amazon Kendra<\/a> is an intelligent search service powered by machine learning. You can receive spelling suggestions for misspelled terms in your queries by utilizing the Amazon Kendra Spell Checker<\/a>. Spell Checker helps reduce the frequency of queries returning irrelevant results by providing spelling suggestions for unrecognized terms.<\/p>\n

In this post, we explore how to use Amazon Kendra Spell Checker on the AWS Management Console<\/a>, as well as how to enable Spell Checker in an Amazon Kendra-powered search application through the AWS Command Line Interface<\/a> (AWS CLI) and AWS SDK.<\/p>\n

Use Amazon Kendra Spell Checker on the console<\/h2>\n

You can automatically receive spelling suggestions for your misspelled Amazon Kendra queries when querying through the console.<\/p>\n

On the Amazon Kendra console, choose your desired index, then choose Search indexed content<\/strong> in the navigation pane. Make sure that the selected index has ingested documents; in this post, we use the sample AWS documentation found in the Data sources<\/strong> section of the navigation pane.<\/p>\n

On the Amazon Kendra search console, simply submit a query as you usually would. Misspelled terms in the query are substituted with suggested terms in the \u201cDid you mean\u201d section of the search console.<\/p>\n

\"\"<\/a><\/p>\n

Choosing the suggested query submits a new query with the corrected spelling.<\/p>\n

\"\"<\/a><\/p>\n

As you can see, the query results provided through the suggested query are significantly more relevant, thanks to Spell Checker!<\/p>\n

Use Amazon Kendra Spell Checker in search applications<\/h2>\n

Search applications powered by Amazon Kendra can quickly and easily enable Spell Checker through the AWS CLI or AWS SDK, which we walk through in this section. Additionally, we go over an example of how to process the Spell Checker response.<\/p>\n

AWS CLI<\/h3>\n

Let\u2019s look at how AWS CLI users can opt in to Amazon Kendra Spell Checker to receive spelling suggestions for misspelled query terms. We use the AWS CLI to query Amazon Kendra as usual, with only one small change: we include the --spell-correction-configuration IncludeQuerySpellCheckSuggestions=true<\/code> argument:<\/p>\n

\n
$ aws kendra query --query-text \"what is knedar\" --index-id [YOUR_INDEX_ID] --spell-correction-configuration IncludeQuerySpellCheckSuggestions=true<\/code><\/pre>\n<\/p><\/div>\n
In addition to the normal query results, the response from Amazon Kendra now contains a SpellCorrectedQueries<\/code> object, if there are any spelling suggestions for the query. For more information, see SpellCorrectedQuery<\/a>.<\/p>\n
\n
\/\/ Full query response omitted for brevity\n\"SpellCorrectedQueries\": [\n  {\n    \"SuggestedQueryText\": \"what is kendra\",\n    \"Corrections\": [\n      {\n        \"BeginOffset\": 8,\n        \"EndOffset\": 14,\n        \"Term\": \"knedar\",\n        \"CorrectedTerm\": \"kendra\"\n      }\n    ]\n  }\n]<\/code><\/pre>\n<\/p><\/div>\n
AWS SDK<\/h3>\n
Next, let\u2019s walk through how Amazon Kendra provides spell check functionality for AWS SDK users. For this example, we use Python 3. We submit a query with a few spelling errors, and print out the SpellCorrectedQueries<\/code> object in the response:<\/p>\n
\n
import boto3\n\nkendra = boto3.client('kendra')\n\nindex_id = '[YOUR_INDEX_ID]'\nquery_text = 'kendra fre teir hours'\nspell_correction_configuration = { 'IncludeQuerySpellCheckSuggestions': True }\n\nresponse = kendra.query(\n  IndexId = index_id,\n  QueryText = query_text,\n  SpellCorrectionConfiguration = spell_correction_configuration\n)\n\nprint(response['SpellCorrectedQueries'])<\/code><\/pre>\n<\/p><\/div>\n
The response from Amazon Kendra now contains the expected spelling suggestions:<\/p>\n
\n
[\n  {\n    'SuggestedQueryText': 'kendra free tier hours', \n    'Corrections': [\n      {\n        'BeginOffset': 7, \n        'EndOffset': 11, \n        'Term': 'fre', \n        'CorrectedTerm': 'free'\n      }, \n      {\n        'BeginOffset': 12, \n        'EndOffset': 16, \n        'Term': 'teir', \n        'CorrectedTerm': 'tier'\n      }\n    ]\n  }\n]<\/code><\/pre>\n<\/p><\/div>\n
Process the Amazon Kendra Spell Check response<\/h3>\n
Now that we\u2019ve gone over how to programmatically get spelling suggestions through either the AWS CLI or AWS SDK, we can examine how we turn the response into a human-readable suggested query. For this example, we use the sample output from the previous section:<\/p>\n
\n
[\n  {\n    'SuggestedQueryText': 'kendra free tier hours', \n    'Corrections': [\n      {\n        'BeginOffset': 7, \n        'EndOffset': 11, \n        'Term': 'fre', \n        'CorrectedTerm': 'free'\n      }, \n      {\n        'BeginOffset': 12, \n        'EndOffset': 16, \n        'Term': 'teir', \n        'CorrectedTerm': 'tier'\n      }\n    ]\n  }\n]<\/code><\/pre>\n<\/p><\/div>\n
Each SpellCorrectedQuery<\/code> has two keys: SuggestedQueryText<\/code> and Corrections<\/code>.<\/p>\n