~/talk

A primer to write a conversational chatbot

Talkat PyCon Israel 2017 · 2017-06-11..06-13· [ai-assisted-development]
links:none on file
slides:none on file

Demonstrates a working chatbot built as a one-endpoint REST service using ChatterBot with NLTK, a CorpusTrainer (greetings, English conversation), Levenshtein best-match and a confidence cutoff of 0.55; basic training takes 5–15 minutes and answers by most-frequent response. Adds Facebook integration via FBMQ with webhook handling and user-profile lookups, supports feedback-based reinforcement learning (like/thumbs-up), shows demos that mostly work but fail on Hebrew and occasionally break during live demo.

AI-written summary · about

  1. 0:00Introduction and background
  2. 2:48History of chatbots
  3. 8:46Modern chatbot trends
  4. 11:59Building a chatbot with ChatterBot
  5. 21:40Facebook Messenger integration
  6. 24:32Demo and Q&A
~/search
type to search 6,249 conferences, 138,987 speakers and 185,172 talks
~/help
cmdctrl k
search every conference, speaker and series
/
focus the filter search
h
home
c
conferences
s
speakers
e
series
t
light / dark — the status bar button does the same
?
this help
esc
close this, then clear every filter — or just the search, while you are typing in it

Ignored while you are typing. Pages without a filter rail have no search to focus.