# Entity extraction of custom entities -- symptoms

**URL:** <https://forum.rasa.com/t/entity-extraction-of-custom-entities-symptoms/38131>\
**Category:** Rasa Open Source\
**Created:** [December 17, 2020, 4:24am UTC](https://forum.rasa.com/t/entity-extraction-of-custom-entities-symptoms/38131 "2020-12-17T04:24:04Z")\
**Posts on this page:** 8\
**Page:** 1

<div class="post-metadata">

**Author:** ![chiqui\_hm](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/chiqui_hm/32/12003_2.png) [@chiqui\_hm](https://forum.rasa.com/u/chiqui_hm)\
**Post date:** [December 17, 2020, 4:24am UTC](https://forum.rasa.com/t/entity-extraction-of-custom-entities-symptoms/38131/1 "2020-12-17T04:24:04Z")

</div>

Hello,

Rasa 2.0 question on extracting entities. I have an intent for when the user informs the assistant of their symptoms:

- intent: enumerate\_symptoms

and a lookup table in my nlu.yml file to improve entity extraction:

- lookup: symptoms

but my assistant can’t seem to extract the entities with the config that I have:

pipeline:

- name: WhitespaceTokenizer

- name: SpacyTokenizer

- name: RegexFeaturizer

- name: LexicalSyntacticFeaturizer

- name: CountVectorsFeaturizer

- name: CountVectorsFeaturizer

- name: DucklingEntityExtractor

- name: CRFEntityExtractor

- name: EntitySynonymMapper

- name: “SpacyNLP”

- name: “SpacyEntityExtractor”

- name: DIETClassifier

 ![image](https://europe1.discourse-cdn.com/flex013/uploads/rasa/original/2X/d/d2a4a882efbe97a3e051eefe29f9e08d83f51b12.png)

I’m wondering if there’s anything wrong with my pipeline? Thanks!

---

<div class="post-metadata">

**Author:** ![ChikkaUdayaSai](https://avatars.discourse-cdn.com/v4/letter/c/85e7bf/32.png) [@ChikkaUdayaSai](https://forum.rasa.com/u/ChikkaUdayaSai)\
**Post date:** [December 17, 2020, 5:06am UTC](https://forum.rasa.com/t/entity-extraction-of-custom-entities-symptoms/38131/2 "2020-12-17T05:06:14Z")

</div>

Yes @chiqui_hm . You have set the entity\_recognition false under DIET classifier.

Remove that and it will work.

---

<div class="post-metadata">

**Author:** ![chiqui\_hm](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/chiqui_hm/32/12003_2.png) [@chiqui\_hm](https://forum.rasa.com/u/chiqui_hm)\
**Post date:** [December 17, 2020, 5:45am UTC](https://forum.rasa.com/t/entity-extraction-of-custom-entities-symptoms/38131/3 "2020-12-17T05:45:36Z")

</div>

Hello, @ChikkaUdayaSai ! I changed it to True but still cannot extract the entities.

---

<div class="post-metadata">

**Author:** ![ChikkaUdayaSai](https://avatars.discourse-cdn.com/v4/letter/c/85e7bf/32.png) [@ChikkaUdayaSai](https://forum.rasa.com/u/ChikkaUdayaSai)\
**Post date:** [December 17, 2020, 5:49am UTC](https://forum.rasa.com/t/entity-extraction-of-custom-entities-symptoms/38131/4 "2020-12-17T05:49:24Z")

</div>

You can remove that entire line that contains entity\_recognition. BTW, have you trained your bot after making the changes. If not, do that.

Let me know once you have finished them.

---

<div class="post-metadata">

**Author:** ![chiqui\_hm](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/chiqui_hm/32/12003_2.png) [@chiqui\_hm](https://forum.rasa.com/u/chiqui_hm)\
**Post date:** [December 17, 2020, 6:07am UTC](https://forum.rasa.com/t/entity-extraction-of-custom-entities-symptoms/38131/5 "2020-12-17T06:07:43Z")

</div>

Hi @ChikkaUdayaSai. yes, I re-trained the model but still not working. is this what you meant by “removing the entire line that contains entity\_recognition”?

- name: DIETClassifier

If yes, it still didn’t extract the entity.

---

<div class="post-metadata">

**Author:** ![kearnsw](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/kearnsw/32/4838_2.png) [@kearnsw](https://forum.rasa.com/u/kearnsw)\
**Post date:** [December 17, 2020, 11:04am UTC](https://forum.rasa.com/t/entity-extraction-of-custom-entities-symptoms/38131/6 "2020-12-17T11:04:05Z")

</div>

Hi @chiqui_hm,

Are you receiving any warnings when you run `rasa train --debug`? It could help if you share the output of that call.

---

<div class="post-metadata">

**Author:** ![chiqui\_hm](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/chiqui_hm/32/12003_2.png) [@chiqui\_hm](https://forum.rasa.com/u/chiqui_hm)\
**Post date:** [December 17, 2020, 12:37pm UTC](https://forum.rasa.com/t/entity-extraction-of-custom-entities-symptoms/38131/7 "2020-12-17T12:37:32Z")

</div>

Hi @kearnsw the model was trained successfully. there’s just this note:

c:\users\clarisse\documents\c19\_venv\venv\lib\site-packages\rasa\utils\tensorflow\model\_data\_utils.py:197: VisibleDeprecationWarning: Creating an ndarray from ragged nested sequences (which is a list-or-tuple of lists-or-tuples-or ndarrays with different lengths or shapes) is deprecated. If you meant to do this, you must specify ‘dtype=object’ when creating the ndarray attribute\_features = {MASK: [np.array(attribute\_masks)]} 2020-12-17 20:32:59 DEBUG rasa.utils.tensorflow.models - Building tensorflow train graph… 2020-12-17 20:33:08 DEBUG rasa.utils.tensorflow.models - Finished building tensorflow train graph. Epochs: 0%| | 0/100 [00:00\<?, ?it/s]c:\users\clarisse\documents\c19\_venv\venv\lib\site-packages\rasa\utils\tensorflow\model\_data.py:587: VisibleDeprecationWarning: Creating an ndarray from ragged nested sequences (which is a list-or-tuple of lists-or-tuples-or ndarrays with different lengths or shapes) is deprecated. If you meant to do this, you must specify ‘dtype=object’ when creating the ndarray final\_data[key][sub\_key].append(np.concatenate(np.array(f)))

---

<div class="post-metadata">

**Author:** ![Naivelearner](https://avatars.discourse-cdn.com/v4/letter/n/90db22/32.png) [@Naivelearner](https://forum.rasa.com/u/Naivelearner)\
**Post date:** [April 16, 2021, 5:30pm UTC](https://forum.rasa.com/t/entity-extraction-of-custom-entities-symptoms/38131/8 "2021-04-16T17:30:53Z")

</div>

Hello Everyone, I am facing the same issue…instead of following all the steps, Entities are not getting extracted. please help