Version: 2.1.x

Language Support

You can use Rasa to build assistants in any language you want.

Your Rasa assistant can be used on training data in any language. If there are no word embeddings for your language, you can train your featurizers from scratch with the data you provide.

In addition, we also support pre-trained word embeddings such as spaCy. For information on what pipeline is best for your use case, check out choosing a pipeline.

Training a Model in Any Language

The following pipeline can be used to train models in any language:

language: "fr" # your two-letter language code
pipeline:
- name: WhitespaceTokenizer
- name: RegexFeaturizer
- name: LexicalSyntacticFeaturizer
- name: CountVectorsFeaturizer
- name: CountVectorsFeaturizer
analyzer: "char_wb"
min_ngram: 1
max_ngram: 4
- name: DIETClassifier
epochs: 100
- name: EntitySynonymMapper
- name: ResponseSelector
epochs: 100

To train a Rasa model in your preferred language, define the pipeline in your config.yml. After you define the pipeline and generate some NLU training data in your chosen language, train the model by running the command:

rasa train nlu

Once the training is finished, you can test your model's language skills. See how your model interprets different input messages by running:

rasa shell nlu
note

Even more so when training word embeddings from scratch, more training data will lead to a better model! If you find your model is having trouble discerning your inputs, try training with more example sentences.

Using Pre-trained Language Models

If you can find them in your language, language models with pre-trained word vectors are a great way to get started with less data, as the word vectors are trained on large amounts of data such as Wikipedia.

spaCy

With the Pre-trained Spacy Embeddings, you can use spaCy's pre-trained language models or load fastText vectors, which are available for hundreds of languages. If you want to incorporate a custom model you've found into spaCy, check out their page on adding languages. As described in the documentation, you need to register your language model and link it to the language identifier, which will allow Rasa to load and use your new language by passing in your language identifier as the language option.

MITIE

You can also pre-train your own word vectors from a language corpus using MITIE. To do so:

  1. Get a clean language corpus (a Wikipedia dump works) as a set of text files.
  2. Build and run MITIE Wordrep Tool_ on your corpus. This can take several hours/days depending on your dataset and your workstation. You'll need something like 128GB of RAM for wordrep to run -- yes, that's a lot: try to extend your swap.
  3. Set the path of your new total_word_feature_extractor.dat as the model parameter in your configuration.

For a full example of how to train MITIE word vectors, check out this blogpost of creating a MITIE model from a Chinese Wikipedia dump.