Question regarding text summarization using various extensions

mohammed1mohammed1 Member Posts: 1 Learner I
edited December 2018 in Help

I am just getting to grips with rapidminer as I would like to use it for my project.  So far, I have been fiddling around with various extensions to try and generate automatic summaries of text that I add to it.  Ideally, I would prefer to add a URL of an article and then receive a summary, however, I received an error along the lines of "wrong number of columns in line 2: was 6 expected, expected 2".  

 

Basically, all I want to create in rapidminer is something that produces a summary like this: https://developer.aylien.com/text-api-demo?text=&language=en&tab=summarize or specifically like this: https://www.researchgate.net/publication/320634202/download

 

The problem is that I do not know what the sequence of processes should be and what parameters I should add (i.e. I know that tokenize, removal of stop words etc should be done, but I am not sure in which exact order).  Could someone please help me or at least point me in the right direction?

Answers

  • lionelderkrikorlionelderkrikor Moderator, RapidMiner Certified Analyst, Member Posts: 1,195 Unicorn

    Hi @mohammed1,

     

    Take a look at this  thread

     

    I hope it helps,

     

    Regards,

     

    Lionel

  • SGolbertSGolbert RapidMiner Certified Analyst, Member Posts: 344 Unicorn

    Hi @mohammed1,

     

     

    I suggest not reinventing the wheel! You already have this functionality in Ayleen and there are also some open source libraries, for example in Python. Integration with existing tools is something that many RM users seem to forget sometimes, but it's a great functionality!

     

    Best regards,

    Sebastian

Sign In or Register to comment.