# Rasa x Arabic language

**URL:** <https://forum.rasa.com/t/rasa-x-arabic-language/46480>\
**Category:** \[Deprecated\] Rasa X Community Edition\
**Created:** [August 3, 2021, 1:00pm UTC](https://forum.rasa.com/t/rasa-x-arabic-language/46480 "2021-08-03T13:00:58Z")\
**Posts on this page:** 8\
**Page:** 1

<div class="post-metadata">

**Author:** ![Rishabhh17](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/rishabhh17/32/16105_2.png) [@Rishabhh17](https://forum.rasa.com/u/Rishabhh17)\
**Post date:** [August 3, 2021, 1:00pm UTC](https://forum.rasa.com/t/rasa-x-arabic-language/46480/1 "2021-08-03T13:00:58Z")

</div>

Hello, I have installed rasa x using docker compose on a azure instance and making changes over GUI like (Intents and all.)Now I want to create a chatbot in “Arabic” language instead of “English” .So I downloaded the BYTEPAIR\_EMBEDDINGS using commands:

pip3 install flair pip3 install bpemb

> > > from flair.embeddings import BytePairEmbeddings embedding = BytePairEmbeddings(‘multi’).

Output:

Setting dim=300 for multilingual BPEmb downloading [https://nlp.h-its.org/bpemb/multi/multi.wiki.bpe.vs100000.model](https://nlp.h-its.org/bpemb/multi/multi.wiki.bpe.vs100000.model) 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1965223/1965223 [00:01\<00:00, 1916803.68B/s] downloading [https://nlp.h-its.org/bpemb/multi/multi.wiki.bpe.vs100000.d300.w2v.bin.tar.gz](https://nlp.h-its.org/bpemb/multi/multi.wiki.bpe.vs100000.d300.w2v.bin.tar.gz) 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 112202964/112202964 [00:08\<00:00, 13721233.23B/s]

> > >

What to do next to create a chatbot for “Arabic”.

---

<div class="post-metadata">

**Author:** ![ChrisRahme](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/chrisrahme/32/15572_2.png) [@ChrisRahme](https://forum.rasa.com/u/ChrisRahme)\
**Post date:** [August 3, 2021, 3:27pm UTC](https://forum.rasa.com/t/rasa-x-arabic-language/46480/2 "2021-08-03T15:27:31Z")

</div>

You can make a chatbot in Arabic the same way as English, with no further steps needed.

I made a [chatbot](https://github.com/ChrisRahme/fyp-chatbot) that speaks English, French, Arabic, Lebanese, and Armenian, without requiring additional steps.

---

<div class="post-metadata">

**Author:** ![Rishabhh17](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/rishabhh17/32/16105_2.png) [@Rishabhh17](https://forum.rasa.com/u/Rishabhh17)\
**Post date:** [August 3, 2021, 5:08pm UTC](https://forum.rasa.com/t/rasa-x-arabic-language/46480/3 "2021-08-03T17:08:48Z")

</div>

You mean like i have to just mention the pipeline like this.

language: ar pipeline:

- name: WhitespaceTokenizer
- name: RegexFeaturizer
- name: LexicalSyntacticFeaturizer
- name: CountVectorsFeaturizer
- name: EmbeddingIntentClassifier intent\_tokenization\_flag: true intent\_split\_symbol: “+”
- name: CountVectorsFeaturizer analyzer: “char\_wb” min\_ngram: 1 max\_ngram: 4
- name: DIETClassifier epochs: 100
- name: EntitySynonymMapper
- name: ResponseSelector epochs: 100

policies:

- name: MemoizationPolicy
- name: RulePolicy
- name: TEDPolicy max\_history: 5 epochs: 100

---

<div class="post-metadata">

**Author:** ![ChrisRahme](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/chrisrahme/32/15572_2.png) [@ChrisRahme](https://forum.rasa.com/u/ChrisRahme)\
**Post date:** [August 3, 2021, 5:10pm UTC](https://forum.rasa.com/t/rasa-x-arabic-language/46480/4 "2021-08-03T17:10:48Z")

</div>

Yup, it even works without mentioning `ar`.

* * *

PS: You can use three backticks (```) a line before and after code to properly format it

````auto
```
Like this
```

````

---

<div class="post-metadata">

**Author:** ![Rishabhh17](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/rishabhh17/32/16105_2.png) [@Rishabhh17](https://forum.rasa.com/u/Rishabhh17)\
**Post date:** [August 3, 2021, 5:18pm UTC](https://forum.rasa.com/t/rasa-x-arabic-language/46480/5 "2021-08-03T17:18:11Z")

</div>

What to mention in language? How it recognize tokenizer , featurizer etc. Like Arabic is different from English. What if some one doesn’t know anything about English and find it difficult to understand the English.

---

<div class="post-metadata">

**Author:** ![ChrisRahme](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/chrisrahme/32/15572_2.png) [@ChrisRahme](https://forum.rasa.com/u/ChrisRahme)\
**Post date:** [August 3, 2021, 5:31pm UTC](https://forum.rasa.com/t/rasa-x-arabic-language/46480/6 "2021-08-03T17:31:54Z")

</div>

> [@Rishabhh17](#):
>
> What to mention in language?

You can mention `language: ar`, I simply said it is not a requirement for it to work.

Like I said previously, my bot speaks English, French, Arabic, Lebanese, and Armenian, and in my pipeline I mentioned `language: en`.

> [@Rishabhh17](#):
>
> How it recognize tokenizer , featurizer etc.

Rasa is language-independent. In the end, it all translates down to 1s and 0s.

 ![image](https://europe1.discourse-cdn.com/flex013/uploads/rasa/original/2X/1/19ee33569b0a609db577d5f2e693b7fc5c5ad5c3.png)

Of course, it’s more complicated than that. Watch the [Rasa Algorithm Whiteboard](https://www.youtube.com/playlist?list=PL75e0qA87dlG-za8eLI6t0_Pbxafk-cxb) playlist to learn more about how stuff works theoretically.

> [@Rishabhh17](#):
>
> What if some one doesn’t know anything about English and find it difficult to understand the English.

I’m not sure what you’re trying to say here. Your bot is capable to understand and talk in Arabic. No English required.

---

<div class="post-metadata">

**Author:** ![Rishabhh17](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/rishabhh17/32/16105_2.png) [@Rishabhh17](https://forum.rasa.com/u/Rishabhh17)\
**Post date:** [August 3, 2021, 5:36pm UTC](https://forum.rasa.com/t/rasa-x-arabic-language/46480/7 "2021-08-03T17:36:53Z")

</div>

Thank you for giving me the reply. I hope it will work for me.

---

<div class="post-metadata">

**Author:** ![ChrisRahme](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/chrisrahme/32/15572_2.png) [@ChrisRahme](https://forum.rasa.com/u/ChrisRahme)\
**Post date:** [August 3, 2021, 5:47pm UTC](https://forum.rasa.com/t/rasa-x-arabic-language/46480/8 "2021-08-03T17:47:24Z")

</div>

Good luck!

You can write your data in Arabic with no problem:

```auto
- intent: greet
  examples: |
    - مرحبا
    - أهلا بك
    - صباح الخير
    - مساء الخير
    - اهلا
    - بونسوار

```

You can also add Arabish:

```auto
- intent: greet
  examples: |
    - kifak
    - ahla
    - ahla w sahla
    - ahlen
    - mar7aba
    - مرحبا
    - أهلا بك
    - صباح الخير
    - مساء الخير
    - اهلا
    - بونسوار

```

And even mix up languages like here: [fyp-chatbot/chitchat.yml at main · ChrisRahme/fyp-chatbot · GitHub](https://github.com/ChrisRahme/fyp-chatbot/blob/main/data/nlu/chitchat.yml)

If it helped you, please mark my answer as solution for future readers 🙂