# Interactive learning with ner\_crf and pre trained extractors

**URL:** <https://forum.rasa.com/t/interactive-learning-with-ner-crf-and-pre-trained-extractors/5166>\
**Category:** Rasa Open Source\
**Created:** [February 13, 2019, 1:19pm UTC](https://forum.rasa.com/t/interactive-learning-with-ner-crf-and-pre-trained-extractors/5166 "2019-02-13T13:19:20Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![mauricedoepke](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/mauricedoepke/32/1961_2.png) [@mauricedoepke](https://forum.rasa.com/u/mauricedoepke)\
**Post date:** [February 13, 2019, 1:19pm UTC](https://forum.rasa.com/t/interactive-learning-with-ner-crf-and-pre-trained-extractors/5166/1 "2019-02-13T13:19:20Z")

</div>

During interactive training the intents found by pre-trained extractors + regex like extractors like spacy and duckling are automatically annotated as entitys. The problem is that spacy and duckling will not profit from this and it might even confuse the ner\_crf extractor.

Is there a way to turn this behaviour off or am I wrong and it is in some way useful for entit extraction? Here an example, where time is extracted by duckling:

Is the NLU classification for 'I need an appointment [from next week wednesday](time:{‘from’: ‘2019-02-20T00:00:00.000+01 :00’, ‘to’: None})from next week wednesday with Intent classification…

---

<div class="post-metadata">

**Author:** ![akelad](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/akelad/32/69_2.png) [@akelad](https://forum.rasa.com/u/akelad)\
**Post date:** [March 3, 2019, 3:00pm UTC](https://forum.rasa.com/t/interactive-learning-with-ner-crf-and-pre-trained-extractors/5166/2 "2019-03-03T15:00:56Z")

</div>

Hmm, do they get saved to the file as well? I know in the json format of NLU, there’s an extractor field and the entities labeled with anything other than `ner_crf` are ignored.

If they do get saved to the file normally though, please raise an issue on Rasa Core