Hello, I am trying to implement an entity extraction model using the CRF extractor. To do so, I have made 2 configurations: one with only sparse features and another one that takes dense features (BERT) as well. Here are the configurations : With sparse features only: pipeline: name: WhitespaceTokenizer name: LexicalSyntacticFeaturizer name: CountVectorsFeaturizer analyzer: char_wb min_ngram: 1 max_ngram: 4 name: CRFEntityExtractor With pre-trained embedding: pipeline: name: HFTransformersNLP model_weights: “bert-base-multilingual-uncased” model_name: “bert” name: LanguageModelTokenizer name: LanguageModelFeaturizer name: CRFEntityExtractor The problem is that I have the exact same results as if the dense features are not being considered at all while I can see it training in the train phase. The same happens when I train it on a different dataset. The rasa version that I’m using is 2.5.1.

CRF with dense features

liaeh (linschen) June 23, 2021, 1:43pm 4

Topic		Replies	Views
Rasa_NLU ner_crf classification issue Rasa Open Source	1	450	June 12, 2019
No Difference in Performance when Using or Changing Language Model Featurizers Rasa Open Source	3	1180	January 17, 2022
CrfExtractor Pipeline Rasa Open Source	3	294	March 19, 2021
Ner_crf Rasa Open Source	12	4973	September 28, 2018
NER_CRF model is not generalizing Rasa Open Source	3	776	December 2, 2019