Text Extraction with Machine Learning

Build text extractors to identify specific data within text, including keywords, entities, features, and more. Structure your data in seconds and avoid manual processing!

video thumbnail
Text Example

“The specs of the laptop are: Refurbished Dell Black 14'' E6420 with Intel Core i5 Processor, 6GB Memory, 320GB Hard Drive and Windows 10 Home”

Automatically Tagged As
DellBrand14''Screen SizeIntel Core i5CPU6GBRAM320GBHard Drive

How to Build Custom Extractors

Easily build and train a machine learning model to recognize and extract text data.

1. Upload Data to MonkeyLearn

Create a model and import your text data by uploading files directly or by connecting with third-party apps.

2. Define Tags

Define the tags you will use for the extractor. These tags will be used to identify the pieces of text to extract.

3. Tag & Train

Train the extractor by tagging the words or phrases you’d like to extract in the text that appears. The extractor will begin to learn right before your eyes.

4. Evaluate & Improve

Test your trained model to see predicted tags. Improve the extractor with more training and by measuring precision and recall.

5. Put Your Classifier to Work

Use your new extractor to analyze new or historical texts. Either upload a file to process text in a batch, use integrations with third-party apps, or our API to extract text automatically.

MonkeyLearn Inc. All rights reserved 2020