I am relatively new to RASA, I am trying to build my very first chatbot and I am still exploring things so I am sorry if I am making beginner mistakes in my pipeline. I am using the pretrained_embeddings pipeline as shown below :
pipeline: - name: SpacyNLP # language model to load model: "en_core_web_md" # when retrieving word vectors, this will decide if the casing # of the word is relevant. E.g. `hello` and `Hello` will # retrieve the same vector, if set to `False`. For some # applications and models it makes sense to differentiate # between these two words, therefore setting this to `True`. case_sensitive: False # - name: "spellChecker.CorrectSpelling" - name: SpacyTokenizer - name: SpacyFeaturizer - 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
The bot can only predict inputs like: “hi” & “hii” as “greet” intent but when I input “hiiii”, the bot fails. I am not sure what to do exactly, I thought CountVectorizer would accommodate for this but somehow it is not working.
Can someone please help me with this, and please tell me how to solve this issue?
Thank you in advance.