Natural Language Processing in a Nutshell

During NLP in a Nutshell workshop we explain how to deal with most topics related to NLP. In the first part we explain some basic methods to handle strings and documents. Different representations are presented and explained. Spacy Data Model is explained and we deeply use Spacy for tokenization and intent recognition. Part of the workshop is to build a NLP pipeline. We use some libraries for sentiment analysis and build our own solution. We show how to deal with German and French languages using some commonly known tools.

Duration: 1 day
Level: beginner

Natural Language Processing in a Nutshell


Group Discounts:

1+2 friends
1500.00PLN   30% off
1+1 friend
1500.00PLN   20% off
Individual measure - Kontaktiere uns


      • Basic Python and Scala knowledge


    • Participants will understand

      • main concepts of Natural Language Processing,
      • benefits of using Python and Scala for NLP application,
      • how to use Natural Language Understanding.
    • Participants will be able to

      • parse and tokenize documents using commonly used tools in Python,
      • use decision trees to do a sentiment analysis in Python,
      • build a NLP pipeline, use Scala and Spark for analysis,
      • build a spam classifier using NLTK,
      • create a custom annotator for a fintech,
      • how to use other language than English in NLP.


  • DAY 1

    • String and Document Processing

      • Advanced regular expression used for text extraction and generation in Python.
      • Understanding Spacy workflow
      • Tokenize using Spacy and NLTK
      • Build a tokenizer with Spark and Scala
    • Text and Vector Representation

      • Understanding One-hot and Term-frequency Representation
      • Word Vectors
    • Text Classification

      • Intent recognition using Spacy
      • Using scikit for text classification
    • Annotators

      • Named Entities Annotators
      • Build custom annotators
  • DAY 2

    • Sentiment Analysis

      • Stanford sentiment analysis tool used for social media texts
      • Build a sentiment analysis method with scikit
    • Pipelines

      • Build a NLP pipeline with Kafka, Spark and Spacy
    • Languages

      • Grammar models and dependencies. Tagging with Spacy
      • Other language than English.
    • Summary and final notes

      • Comparing of available tools and usage


Trainer image

Karol Przystalski

Chief Technology Officer

Karol Przystalski is CTO and founder of Codete. He obtained a Ph.D in Computer Science from the Institute of Fundamental Technological Research, Polish Academy of Sciences, and was a research assistant at Jagiellonian University in Cracow. His role at Codete is focused on leading and mentoring teams. The company has built a research lab that is working on machine learning methods and big data solutions in specialty areas such as pattern recognition and HDP implementation.



contact person

Olga Sroka

Workshop Advisor

mail icon

phone icon width=   +48 888 011 177

contact person

Maciej Szczepański

Workshop Advisor

mail icon

phone icon width=   +48 606 42 14 76

This value should not be blank.
This value should not be blank.
Form has been submitted.
Failed to send message - please try