Hi, so I have a lookup tables with entities and also included every example of them in an example sentence. But if I ask the bot a question using an entity which is not included in the lookup table, it still recognizes is as the according entity. I think I am having the wrong pipeline, so that’s my config file:
pipeline: - name: SpacyNLP - 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: DucklingHTTPExtractor url: http://localhost:8000 dimensions: - time - number - ordinal locale: de_DE timezone: Europe/Berlin timeout: 3 - name: ResponseSelector epochs: 100 policies: - name: MemoizationPolicy - name: TEDPolicy - name: MappingPolicy - name: FormPolicy - name: FallbackPolicy nlu_threshold: 0.4 core_threshold: 0.3 fallback_action_name: action_default_fallback
Can someone help?