10. • Simple to develop
• Asynchronous notifications
• Integrates with team
Chatbot advantages
11. How does it work?
User makes a request Request analyzed
by artificial intelligence
User info taken into account
(history, preferences…)
Real time response
Conversational strategy
Interactions personalization
…
12. TWO TYPES OF CHATBOTS
1. Based on rules
2. Based on Artificial
intelligence
16. Cont,
…
Text &/or Speech Engine
Natural Language
Processing
Machine and
Deep Learning
AI Engine #1: Natural Language Processing (NLP)
NLP enables computers to derive meaning from human or natural
language input.
17. Cont,
…
Text &/or Speech Engine
Natural Language
Processing
Machine and
Deep Learning
AI Engine #2: Machine Learning (ML)
ML enables computers to learn when exposed to new data without
being explicitly programmed.
18.
19.
20.
21. Cont,
…
Text &/or Speech Engine
Natural Language
Processing
Machine and
Deep Learning
AI Engine #1: Natural Language Processing (NLP)
NLP enables computers to derive meaning from human or natural
FIRST GENERATION
CHATBOT CAPABILITIES AND
CHALLENGES
22. Cont,
…
Text &/or Speech Engine
Natural Language
Processing
Machine and
Deep Learning
AI Engine #1: Natural Language Processing (NLP)
NLP enables computers to derive meaning from human or natural
Intent Recognition (classification)
“the ability to understand the intent from human ambiguous
language”
#wordvector, #deeplearning4j, #opennlp, #stanfordnlp
23. Cont,
…
Text &/or Speech Engine
Natural Language
Processing
Machine and
Deep Learning
AI Engine #1: Natural Language Processing (NLP)
NLP enables computers to derive meaning from human or natural
Cont,
Advance Intent Recognition Challenge
“The city councilmen refused the demonstrators a permit because they feared violence”
“What does the word “they” refer to here — the councilmen or the demonstrators? What if instead of “feared”
we wrote “advocated”?”(1)
“Oren Etzioni: When AI can’t determine what “it” refers to in a sentence, it’s hard to believe that it will take over
the world”(1)
24. Cont,
…
Text &/or Speech Engine
Natural Language
Processing
Machine and
Deep Learning
AI Engine #1: Natural Language Processing (NLP)
NLP enables computers to derive meaning from human or natural
Cont,
Intent Recognition Training Model Guideline
“intents should be different enough to help the ML disambiguate better”
“Good Pizza vs Bad Pizza are not two different intents, the intent here would be Pizza Quality, Good and Bad would
be entity Rating”
“single keywords are not useful”
“unique sentences are super helpful, semantically and synonym rich”
“do {word} sentence construction in different intent models will falsely give high prediction score for all intents”
25. Cont,
…
Text &/or Speech Engine
Natural Language
Processing
Machine and
Deep Learning
AI Engine #1: Natural Language Processing (NLP)
NLP enables computers to derive meaning from human or natural
Cont,
Entity Recognition (NER)
“the ability to automatically recognize entity meanings from ambiguous language”
“despite all improvements in ML, the problem of accurate entity recognition is far from been solved”
“main effort currently is directed to find approaches to reduce the annotation labor – semi-supervised NER”
#opennlp, #stanfordnlp
26. Cont,
…
Text &/or Speech Engine
Natural Language
Processing
Machine and
Deep Learning
AI Engine #1: Natural Language Processing (NLP)
NLP enables computers to derive meaning from human or natural
Cont,
Entity Recognition (NER) – example with OpenNLP
Model
“The other day at work I saw <START:person> Larry Elison <END> at <START:building> HQ600 <END>”
Test
“The other day at work I saw Lyudmil Pelov at HQ300”
“The other day at work I saw lyudmil Pelov at 300”
27. Cont,
…
Text &/or Speech Engine
Natural Language
Processing
Machine and
Deep Learning
AI Engine #1: Natural Language Processing (NLP)
NLP enables computers to derive meaning from human or natural
Cont,
Sentiment Analysis (emotional intelligence)
“evaluate subjective patterns and expressions of sentiment within textual content”
“usually identifies if expression was positive, negative, mixed, or neutral”
“requires a high degree of supervised ML on big data corpus, usually Twitter”
#deeplearning4j, #opennlp, #stanfordnlp
28. Cont,
…
Text &/or Speech Engine
Natural Language
Processing
Machine and
Deep Learning
AI Engine #1: Natural Language Processing (NLP)
NLP enables computers to derive meaning from human or natural
Cont,
Probabilistic Parser
“probabilistic parsing is using dynamic programming algorithms to compute the most likely parse(s) of a given
sentence, given a statistical model of the syntactic structure of a language”
“parse any address, name, number, date or any unstructured text in useful components”
#stanford, #duckling, #parserator
29. Cont,
…
Text &/or Speech Engine
Natural Language
Processing
Machine and
Deep Learning
AI Engine #1: Natural Language Processing (NLP)
NLP enables computers to derive meaning from human or natural
Cont,
Probabilistic Parser – Duckling Example
#stanford, #duckling, #parserator
31. Movie Usher bot
Movie Usher Bot will be your usher in the world of
cinema,it will help you to get your favorite movie,
also it can recommending movies to you based
on your mode or genres,
and it will help you to get information about movies
By the way it is Available now on Messenger :)
…