Separate words keep merging when using text processeing extension.


Does anyone know why words keep merging together during/after preprocessing, such as after executing the POS tagger? This is a huge pain that I can’t figure out. For example, the words below were once separated but have merged into one giant Frankenstein word.

  • Example 1 before: “Burnout: Better acceptance of staff mental health issues, in regards to sick time."

  • Example 1 after: ‘: “burnoutacceptance staff mental health issueregards sick time”

  • Example 2 before: "Physical, mental, emotional stress/burnout

  • Example 2 after: ‘physicalmentalemotional stressburnout"

Thanks in advance,

Hi Cyrprano!

Can you tell me a little bit about your preprocessing procedure?

If I just use these sentences followed by the POS tagger, I don’t get the same results

Thanks! I think the issue worked itself out somehow. My output seems fine now.

1 Like