When using the sentence extractor node against a column of customer comments (multiple sentences) that I have ran through the strings to documents node then the sentence extractor. I see the output of the sentenec extractor also contains the original comment (multiple sentemces) in the sentence extraction. How do I remove this original comment from the snetence output?
Dear Jim Luckas:
I raised a similar issue and the response from Kilian was as follows. You could access the example workflow by accessing the threat dated 08/06/2014. The title of the post is Sentence Extractor Node.
In case you have problems accessing the above post, let me know and I could fish out the example workflow from Kilian and forward it to you.
Cheers
QUOTE:
Hi Sridhar,
the Sentence Extractor node extracts all sentences from documents. The title of a document is considered as a sentence as well and gets extracted too. You can mark the title rows in the output table and detect when sentences of a new documents will appear, by using a little bit of Java code with the Java Snippet node. Based on these markers you can filter out the title rows.
Attached is an example workflow.
Cheers, Kilian
UNQUOTE
Dear Sridhar,
Thank you so much. I found the example workflow from Kilian and it solved my issue. I guess I was just a little confused when I read the post before I submitted my post as it was talking about title but now it makes sense.
This topic was automatically closed 90 days after the last reply. New replies are no longer allowed.