# If I want to use spacy for extracting name then what would the config file looks like?

**URL:** <https://forum.rasa.com/t/if-i-want-to-use-spacy-for-extracting-name-then-what-would-the-config-file-looks-like/36903>\
**Category:** Rasa Open Source\
**Created:** [November 11, 2020, 11:38am UTC](https://forum.rasa.com/t/if-i-want-to-use-spacy-for-extracting-name-then-what-would-the-config-file-looks-like/36903 "2020-11-11T11:38:10Z")\
**Posts on this page:** 1\
**Showing post:** 22

<div class="post-metadata">

**Author:** ![koaning](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/koaning/32/6626_2.png) [@koaning](https://forum.rasa.com/u/koaning)\
**Post date:** [November 26, 2020, 9:20am UTC](https://forum.rasa.com/t/if-i-want-to-use-spacy-for-extracting-name-then-what-would-the-config-file-looks-like/36903/22 "2020-11-26T09:20:51Z")

</div>

I think in this case spaCy won’t be able to help much. Also, [note the question here](http://forum.rasa.com/t/family-name-extraction/36945/9). The French spaCy model doesn’t seem to be great at finding Arabic names. It’s likely the French model overfits names from France because that’s what it has been trained on.

I’ll be picking this up as a task for rasa-nlu-examples [here](https://github.com/RasaHQ/rasa-nlu-examples/issues/64). Probably the simplest solution is to host the most frequent names per country such that folks can easily link that to a RegexEntityExtractor.

---

_[View the full topic](https://forum.rasa.com/t/if-i-want-to-use-spacy-for-extracting-name-then-what-would-the-config-file-looks-like/36903)._
