Using fasttext pretrained word emmbeding for other language

Hi all,

Is there any detail on how to implement fasttext like suggested here?

https://rasa.com/docs/rasa/nlu/language-support/#spacy

I found a couple of text about this but seems it’s like dead end.

I have already download all the stuff that i need just need to know how to use it from pipeline.

@Juste @amn41

Cheers

I think I’ve answereed a similar question elsewhere. But just for completeness, you can use rasa nlu examples for this.

yes… sorry for that… double posting… this one is an old post.

thanks. trying that right now. downloading… :slight_smile:

I tried this with Finnish language, but no success. Followed this example https://rasahq.github.io/rasa-nlu-examples/docs/featurizer/fasttext/

This is the error message when I do “rasa train --debug”

Core model training completed. Training NLU model… Traceback (most recent call last): File “/home/linttu/miniconda3/lib/python3.7/site-packages/rasa/nlu/registry.py”, line 173, in get_component_class return class_from_module_path(component_name) File “/home/linttu/miniconda3/lib/python3.7/site-packages/rasa/utils/common.py”, line 210, in class_from_module_path m = importlib.import_module(module_name) File “/home/linttu/miniconda3/lib/python3.7/importlib/init.py”, line 127, in import_module return _bootstrap._gcd_import(name[level:], package, level) File “”, line 1006, in _gcd_import File “”, line 983, in _find_and_load File “”, line 953, in _find_and_load_unlocked File “”, line 219, in _call_with_frames_removed File “”, line 1006, in _gcd_import File “”, line 983, in _find_and_load File “”, line 953, in _find_and_load_unlocked File “”, line 219, in _call_with_frames_removed File “”, line 1006, in _gcd_import File “”, line 983, in _find_and_load File “”, line 965, in _find_and_load_unlocked ModuleNotFoundError: No module named ‘rasa_nlu_examples’

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File “/home/linttu/miniconda3/bin/rasa”, line 8, in sys.exit(main()) File “/home/linttu/miniconda3/lib/python3.7/site-packages/rasa/main.py”, line 92, in main cmdline_arguments.func(cmdline_arguments) File “/home/linttu/miniconda3/lib/python3.7/site-packages/rasa/cli/train.py”, line 76, in train additional_arguments=extract_additional_arguments(args), File “/home/linttu/miniconda3/lib/python3.7/site-packages/rasa/train.py”, line 50, in train additional_arguments=additional_arguments, File “uvloop/loop.pyx”, line 1456, in uvloop.loop.Loop.run_until_complete File “/home/linttu/miniconda3/lib/python3.7/site-packages/rasa/train.py”, line 101, in train_async additional_arguments, File “/home/linttu/miniconda3/lib/python3.7/site-packages/rasa/train.py”, line 188, in _train_async_internal additional_arguments=additional_arguments, File “/home/linttu/miniconda3/lib/python3.7/site-packages/rasa/train.py”, line 245, in _do_training persist_nlu_training_data=persist_nlu_training_data, File “/home/linttu/miniconda3/lib/python3.7/site-packages/rasa/train.py”, line 482, in _train_nlu_with_validated_data persist_nlu_training_data=persist_nlu_training_data, File “/home/linttu/miniconda3/lib/python3.7/site-packages/rasa/nlu/train.py”, line 75, in train trainer = Trainer(nlu_config, component_builder) File “/home/linttu/miniconda3/lib/python3.7/site-packages/rasa/nlu/model.py”, line 142, in init components.validate_requirements(cfg.component_names) File “/home/linttu/miniconda3/lib/python3.7/site-packages/rasa/nlu/components.py”, line 51, in validate_requirements component_class = registry.get_component_class(component_name) File “/home/linttu/miniconda3/lib/python3.7/site-packages/rasa/nlu/registry.py”, line 199, in get_component_class raise ModuleNotFoundError(exception_message) ModuleNotFoundError: Failed to find module ‘rasa_nlu_examples.featurizers.dense’. No module named ‘rasa_nlu_examples’

Here are my config files

language: fi

pipeline:

  • name: WhitespaceTokenizer
  • name: LexicalSyntacticFeaturizer
  • name: CountVectorsFeaturizer analyzer: char_wb min_ngram: 1 max_ngram: 4
  • name: rasa_nlu_examples.featurizers.dense.FastTextFeaturizer cache_dir: downloaded/beforehand file: cc.fi.300.bin
  • name: DIETClassifier epochs: 100

policies:

  • name: MemoizationPolicy
  • name: KerasPolicy
  • name: MappingPolicy

Here is location of my finnish language fastext file (base) linttu@linttu-VirtualBox:~/rasaTest/fastText/downloaded/beforehand$ ls -l total 7073864 -rw-r–r-- 1 linttu linttu 7243629925 elo 18 19:13 cc.fi.300.bin