In which case would you want to use LexicalSyntacticFeaturizer in your pipeline?

Rasa Open Source
1

I have read about LexicalSyntacticFeaturizer in the documentation, and it is also available as a default option in the pipeline. I wanted to know when someone would want to use this Featurizer, so I could understand it better.

Thanks for your time!

1 Like
2

@BrookieHub Hi!

The LexicalSyntacticFeaturizer is a component that we recommend starting out with. In many cases, it helps detect entities because of the features that it is able to extract.

In short : Creates lexical (relating to the words or vocabulary of a language) and syntactic (according to syntax) features for a user message to support entity extraction.

A tokenizer is used to split the input text into words. A featurizer transforms the tokens as well as some of their properties into features that can be used by machine learning algorithms. A named entity recognizer (ner) extracts entities (e.g. names, quantities, dates, etc.) from the input.

For more detail concept about LexicalSyntacticFeaturizer you can see this blog : Lexical Features from SpaCy for Rasa | Rasa

I hope this you already seen and understood about LexicalSyntacticFeaturizer : Components

You can even see this Github link for code: https://github.com/RasaHQ/rasa/blob/main/rasa/nlu/featurizers/sparse_featurizer/lexical_syntactic_featurizer.py

I hope this will help you understand this concept and solve your topic. Good Luck!

2 Likes
3

Thanks a lot for the explanation and the link share. That solved my problem :D!