Implementation
Munirah-kh opened this issue · 9 comments
Hello
I have code for rasa chatbot in English language but, when i run the code for Arabic language there is an error
So could u please tell me how to integrate the code u provided with the steps to train and run the chatbot for Arabic language
Thank you
Could you share the Arabic config.yml
file that you tried?
I think the standard pipeline that comes with rasa init
theoretically should be a reasonable baseline. Arabic is whitespace-separated, right?
What version of python/Rasa are you using?
Also, please refrain from using screenshots to share code. Screenshots cannot be copied/pasted/indexed/searched.
To my knowledge spaCy does not support Arabic. Could you replace the spaCy tokenizer with a whitespace tokenizer and remove all spaCy components?
Python: 3.6.8
rasa Version: 2.3.0
this is an example of Arabic language : مرحبا بكم
how can i install whitespace tokenizer ?
It comes with Rasa, no need for an extra install. Could you try this one for your pipeline
segment?
pipeline:
# # No configuration for the NLU pipeline was provided. The following default pipeline was used to train your model.
# # If you'd like to customize it, uncomment and adjust the pipeline.
# # See https://rasa.com/docs/rasa/tuning-your-model for more information.
- name: WhitespaceTokenizer
- name: RegexFeaturizer
- name: LexicalSyntacticFeaturizer
- name: CountVectorsFeaturizer
- name: CountVectorsFeaturizer
analyzer: char_wb
min_ngram: 1
max_ngram: 4
- name: DIETClassifier
epochs: 100
constrain_similarities: true
- name: EntitySynonymMapper
- name: ResponseSelector
epochs: 100
Ok I’ll try it and reply back
Thank you
I'll close the issue in the meantime since this question isn't about this repository.
For future help, please add a ticket on our forum: https://forum.rasa.com.