Developing Bots. Primers

Developing Bots. Primers

During the workshop, we implement three different types of bots. We have prepared a few notebooks to be done before the course to the participants a short introduction into chatbots. We implement an HR assistant bot that can be a basis for your projects.

At the beginning of day on one of the courses we present bot taxonomy and machine learning terms related to bots. Next, we go through natural language processing and natural language understanding. During the training, we go also into more complex topics like sentiment analysis, context management and how to build intelligent bots. We show how to develop a vectorizer and build a sentiment analysis method. This method is next compared with other solutions that are available on the market. The context management is a complex topic and we show how to use some methods to deal with context recognition and management in case we have more than one.

Prerequisites

• Basic Python knowledge,
• Recommended: basic machine learning knowledge

Outcomes

Participants will understand…

• how to use NLP methods,
• how machine learning methods are used for bots,
• generative and relative approaches to NLU,
• how to use sentiment analysis.

Participants will be able to…

• develop their own bot using common tools like NLTK, Rasa and spaCy

Agenda

Introduction - 30 min.

• Introduction to bots
• Machine learning and bots

Natural Language Processing - 90 min. Five exercises

• Regular expressions and Python methods used for text processing
• Corporas, NLTK, and tokenization
• Part of Speech and Tagging - examples with NLTK and Spacy
• Text normalization
• Lemmatization
• Sentence extraction
• Noun chunks
• Named Entity Recognition
• TF-IDF and bag of words

Natural Language Understanding - 180 min. Three exercises

• Similarity measures
• Vector Space Model explained
• Type of vectorizers
• Understanding One-hot and Term-frequency Representation
• Word Vectors
• Build a vectorizer with Tensorflow
• Intent and entities in NLU explained
• Using SpaCy language model and Rasa for intent understanding

Context management and chatbots - 210 min. Three exercises

• Introduction to the problem of context management
• Use similarity measure to get the context of the conversation
• Using Intents in context management with Rasa NLU
• Implementation of a neural network for context recognition
• Managing context with Rasa NLU

Duration

1-day workshop

We provide a delicious complimentary meal, coffee, and snacks.

If you have any further questions please contact us via [email protected]