Options

Sentence Analysis

Paul_WhittakerPaul_Whittaker Member Posts: 2 Contributor I
edited November 2018 in Help
Hello

I have documents that contain an identifier and a sentence of words. I've broken the sentences into individual words using Tokenize from the Text Analysis module, but I would also like to tag each word with the original sentence identifier that it came from.

The second question is that I although I have the individual words, I would like some way of checking for phrases i.e. relationships between the words.

Any help at all would be really really appreciated.

Many Thanks
Paul

Answers

  • Options
    landland RapidMiner Certified Analyst, RapidMiner Certified Expert, Member Posts: 2,531 Unicorn
    Hi Paul,
    unfortunately this isn't possible right now. But we have already planned to extend the Text Processing Capabilities to such a point, a detailed plan lies on my desk. So it's only a matter of time when it can be done with RapidMiner :)
    Anyway, if you have a strong desire for some specific feature and need it as soon as possible, we are always offering the service of making individual extensions or adapting existing ones to your needs.

    Greetings,
      Sebastian
  • Options
    Paul_WhittakerPaul_Whittaker Member Posts: 2 Contributor I
    Many thanks Sebastian - Out of interest, roughly how much would it cost to get an individual extension? Currently I'm re-matching the words back to the original sentences at the database end and it takes a very long time. Feel free to email me at paulwhittaker99@hotmail.com.

    Thanks
    Paul
Sign In or Register to comment.