# Wrong Intent Classified - to certain data set

**URL:** <https://forum.rasa.com/t/wrong-intent-classified-to-certain-data-set/36891>\
**Category:** Rasa Open Source\
**Created:** [November 11, 2020, 8:07am UTC](https://forum.rasa.com/t/wrong-intent-classified-to-certain-data-set/36891 "2020-11-11T08:07:23Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![MohanSampagaon](https://avatars.discourse-cdn.com/v4/letter/m/e495f1/32.png) [@MohanSampagaon](https://forum.rasa.com/u/MohanSampagaon)\
**Post date:** [November 11, 2020, 8:07am UTC](https://forum.rasa.com/t/wrong-intent-classified-to-certain-data-set/36891/1 "2020-11-11T08:07:23Z")

</div>

Hello, nlu is identifying wrong intent for below example, please guide if I am missing something

nlu.md ##intent:pfContrib

- What is the provident fund contribution to be made by the employee and employer in the Provident Fun
- employer pf contribution
- employee contribution
- how much does employee contribute for pf
- employee employer contribute towards
- employee employer pf contribution

##intent:pfContact

- whom do I contact for pf queries
- contact for pf
- whom do I reach for pf queries
- pf contact
- pf contact person

When I try giving ( error is only for below input) pf contribution -\> intent recognized is pfContact but when I give contribution to pf -\> correct intent is recognized.

Pipeline:

# Configuration for Rasa NLU.

# [https://rasa.com/docs/rasa/nlu/components/](https://rasa.com/docs/rasa/nlu/components/)

language: en pipeline:

- name: WhitespaceTokenizer
- name: RegexFeaturizer
- name: LexicalSyntacticFeaturizer
- name: CountVectorsFeaturizer analyzer: “char\_wb” min\_ngram: 1 max\_ngram: 4
- name: DIETClassifier epochs: 100
- name: EntitySynonymMapper
- name: ResponseSelector epochs: 100

# Configuration for Rasa Core.

# [https://rasa.com/docs/rasa/core/policies/](https://rasa.com/docs/rasa/core/policies/)

policies:

- name: KerasPolicy
- name: TEDPolicy max\_history: 5 epochs: 100
- name: AugmentedMemoizationPolicy
- name: MappingPolicy
- name: FallbackPolicy nlu\_threshold: 0.4 core\_threshold: 0.4 fallback\_action\_name: “action\_default\_fallback”

---

<div class="post-metadata">

**Author:** ![wafaa](https://avatars.discourse-cdn.com/v4/letter/w/e19b73/32.png) [@wafaa](https://forum.rasa.com/u/wafaa)\
**Post date:** [November 11, 2020, 10:04am UTC](https://forum.rasa.com/t/wrong-intent-classified-to-certain-data-set/36891/2 "2020-11-11T10:04:19Z")

</div>

Hi @ [MohanSampagaon](https://forum.rasa.com/u/MohanSampagaon) may be you need train the model with more stories. you can edit the prediction using ‘Rasa X’ and save it.