- Newest
- Most votes
- Most comments
Comprehend is not a search tool. It is an API that will make it easy to :
- Detect the dominant language
- Detect named entities
- Detect key phrases
- Determine sentiment
- Analyze targeted sentiment
- Detect syntax
- Detect events
- Do Topic modeling
from documents you provide through the real-time or batch API. It will provide json formatted response containing the inferred elements. For instance:
{
"LanguageCode": "en",
"KeyPhrases": [
{
"Text": "today",
"Score": 0.89,
"BeginOffset": 14,
"EndOffset": 19
},
{
"Text": "Seattle",
"Score": 0.91,
"BeginOffset": 23,
"EndOffset": 30
}
]
}
Notice that the response contains BeginOffset and EndOffset which tell you where the entity was detected in the document should you want to pull the text (or more text arround it) from the document. If your objective is to do natural language full text search on documents, I'd recommend looking into Amazon Kendra (https://aws.amazon.com/kendra/)
If you want to see both these solutions in action to provide Knowledge extraction and natural language search powered by AI/ML you can check out the Document Understanding Solution : https://aws.amazon.com/solutions/implementations/document-understanding-solution/
Relevant content
- asked 2 years ago
- AWS OFFICIALUpdated 2 years ago
- AWS OFFICIALUpdated a year ago
- AWS OFFICIALUpdated 2 years ago
- AWS OFFICIALUpdated a year ago