# CRFEntityExtractor or DIETClassifier splits one entity into multiple words

**URL:** <https://forum.rasa.com/t/crfentityextractor-or-dietclassifier-splits-one-entity-into-multiple-words/34334>\
**Category:** Rasa Open Source\
**Created:** [September 24, 2020, 1:11pm UTC](https://forum.rasa.com/t/crfentityextractor-or-dietclassifier-splits-one-entity-into-multiple-words/34334 "2020-09-24T13:11:17Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![ridhimagarg](https://avatars.discourse-cdn.com/v4/letter/r/f14d63/32.png) [@ridhimagarg](https://forum.rasa.com/u/ridhimagarg)\
**Post date:** [September 24, 2020, 1:11pm UTC](https://forum.rasa.com/t/crfentityextractor-or-dietclassifier-splits-one-entity-into-multiple-words/34334/1 "2020-09-24T13:11:17Z")

</div>

I updated from RASA 1.10.2 to 1.10.14.

My pipeline is -:

```
language: en
pipeline:
  - name: SpacyNLP
    model: en_core_web_md
  - name: ConveRTTokenizer
  - name: ConveRTFeaturizer
  - name: RegexFeaturizer
  - name: LexicalSyntacticFeaturizer
  - name: CRFEntityExtractor
  - name: DIETClassifier
    epochs: 50
  - name: EntitySynonymMapper
  - name: ResponseSelector
    epochs: 100
  - name: SpacyEntityExtractor
  - name: "DucklingHTTPExtractor"
    url: "http://0.0.0.0:8000"
    locale: "en_GB"
    timezone: "US/Pacific"
    timeout : 3

```

In RASA 1.10.2 CRFEntityExtractor was working fine but in 1.10.14 it is splitting the entity into multiple tokens.

Pls help

If more information for nlu data is required will provide.

Thanks!

---

<div class="post-metadata">

**Author:** ![ridhimagarg](https://avatars.discourse-cdn.com/v4/letter/r/f14d63/32.png) [@ridhimagarg](https://forum.rasa.com/u/ridhimagarg)\
**Post date:** [September 25, 2020, 6:27am UTC](https://forum.rasa.com/t/crfentityextractor-or-dietclassifier-splits-one-entity-into-multiple-words/34334/2 "2020-09-25T06:27:05Z")

</div>

Looking for a help @RASA Team.

---

<div class="post-metadata">

**Author:** ![UlisesVD](https://avatars.discourse-cdn.com/v4/letter/u/8e7dd6/32.png) [@UlisesVD](https://forum.rasa.com/u/UlisesVD)\
**Post date:** [September 25, 2020, 5:52pm UTC](https://forum.rasa.com/t/crfentityextractor-or-dietclassifier-splits-one-entity-into-multiple-words/34334/3 "2020-09-25T17:52:47Z")

</div>

check this post: [Introducing DIET: state-of-the-art architecture that outperforms fine-tuning BERT and is 6X faster to train](https://blog.rasa.com/introducing-dual-intent-and-entity-transformer-diet-state-of-the-art-performance-on-a-lightweight-architecture/)

---

<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:** [October 5, 2020, 7:49am UTC](https://forum.rasa.com/t/crfentityextractor-or-dietclassifier-splits-one-entity-into-multiple-words/34334/4 "2020-10-05T07:49:47Z")

</div>

I think there’s an issue by using `spacy` together with `convert`. They each come with their own tokenizer and I can imagine that they’re not playing nice with eachother. I also wonder, is there a particular reason you’re using the spaCy entity extractor? Are there specific entities that are pretrained in `en_core_web_md` that you’re interested in?