Hi
Does anyone have an illustrative workflow for discovering collocations or multiword expressions from text documents?
TIA
Peter
There is no Multiword recognizer/tagger node so far, which detects multiwords based on statistical methods (e.g. co-occurrences). You can use e.g. the OpenNLP NE tagger (or Abner tagger) to find (and tag) named entities and filter them afterwards.
- Kilian
This topic was automatically closed 90 days after the last reply. New replies are no longer allowed.