🎉 🎉 RAPIDMINER 9.10 IS OUT!!! 🎉🎉

Download the latest version helping analytics teams accelerate time-to-value for streaming and IIOT use cases.

CLICK HERE TO DOWNLOAD

Entity Extraction with Process Documents

JeffChowaniecJeffChowaniec Employee, Member Posts: 13  RM Data Scientist
edited November 2018 in Knowledge Base

Entity Extraction:

 

Using the Text mining extension and coupled process documents operators, we can build a process for entity extraction.

 

Requirements:

  • Text Processing Extension
  • Text file of entities to be extracted
  • Text file to extract

For the entity file, a simple CSV where each line is an individual entity

 

Step 1:

Read CSV - Call our entity CSV file

Process documents from data - send the read CSV into the process documents

entityextractoin1.png

Inside the process documents from data we will need a filter tokens and a transform cases (lowercase)

 

Step 2: 

 

Using the word list output from step one, we connect it to a Process Documents operator to extract the word list from the text.

EntityExtraction2.png

Thomas_Ott

Comments

  • bieha95_nsabieha95_nsa Member Posts: 10 Contributor I

    On step 2: what process involved in the second 'process document and after that, how to do to create the document ?

     

    Other question, after create the document (there is sentence that we want to extract).

    How to do matching the sentence with database use?

Sign In or Register to comment.