Hi, I am using DIET Classifier for entity extraction. However it is extracting an entity twice whereas both combined is the actual entity. Please let me know how to resolve this. Below is the output:
Received user message 'get site Washington DC' with intent '{'name': 'show_sites', 'confidence': 0.9747471809387207}' and entities '[{'entity': 'sitename', 'start': 9, 'end': 19, 'confidence_entity': 0.7346358895301819, 'value': 'Washington', 'extractor': 'DIETClassifier'}, {'entity': 'sitename', 'start': 20, 'end': 22, 'confidence_entity': 0.5150449872016907, 'value': 'DC', 'extractor': 'DIETClassifier'}]'
NLU Pipeline:
- name: SpacyNLP
model: en_core_web_md
case_sensitive: False
- name: SpacyTokenizer
- name: SpacyFeaturizer
- name: RegexFeaturizer
- name: CountVectorsFeaturizer
analyzer: "char_wb"
min_ngram: 1
max_ngram: 4
- name: SklearnIntentClassifier
- name: RegexEntityExtractor
use_lookup_tables: True
use_regexes: True
- name: DIETClassifier
epochs: 100
constrain_similarities: true
- name: EntitySynonymMapper
- name: ResponseSelector
epochs: 100
constrain_similarities: true
- name: FallbackClassifier
threshold: 0.5
ambiguity_threshold: 0.1