Karol explains shortly different aspects of machine learning methods used for bots. The topics that are covered during this session are natural language understanding, sentiment analysis, conversation management and pattern recognition. The main part is dedicated to generative models that are the current trend when it comes to chatbots. A taxonomy of generative models is presented. The presentation is concluded with an explanation on how to use deep learning methods to extend a chatbot to be more intelligent.
4. Rule-based
Phrases list
Show status of recruitment.
What is the weather in Berlin?
Hi!
Hire candidate <name>.
No valid phrase found
Answers list
We have currently X candidates.
It is <current weather>.
Hi. How are you?
Sent an email to <email>.
7. Retrieval-based
Advantages
✓ identify the intent
✓ usually easy to train
✓ does not need too many
questions/answers
✓ more intelligent than rule-based
Bottlenecks/Challanges
⟶ limited to questions/answers
11. Comparison
⟶ don’t use a solution/approach because it’s cool!
⟶ in many cases classic machine learning methods are good enough and
generative models does not need to be used
⟶ generative models are good if we are looking for a more generic solution and
have a lot of data to be used for training
12. Where to go next ...
To learn more about bots and how build one, please register for Developing
bots primers workshop: workshops.codete.com. It’s free.
Read Pattern recognition Primer, Springer 2018 book. It will be published in
Spring 2018.
Looking for ideas or advices? Find me at our booth at Data Natives conference.