Building companion chatbot with Python

Mimansa Jaiswal (~mimansa)




This talk would cover the intricacies of developing a chat bot with python and pyAIML.

Though we are not yet on the brink of great development as shown in robotic movies, chatbots have been marching ahead

The talk aims to cover the following points:

(1 )What is pyAIML. The XML dialect called AIML was developed by Richard Wallace and a worldwide free software community between 1995 and 2002. AIML formed the basis for what was initially a highly extended Eliza called "A.L.I.C.E.." ("Artificial Linguistic Internet Computer Entity"), which won the annual Loebner Prize Competition in Artificial Intelligence[3] three times, and was also the Chatterbox Challenge[4] Champion in 2004.

(2) It would then go on to how to use standard and create a standard startup file, creating an AIMl file and generating random responses.

(3) Then I would move on to integration of python, adding sessions and predicates in the XML file. I would then demo a very basic chatbot in python.

(4) I would then introduce different packages which could be useful,, chatterbot.

(5) I would then also show an example of using pywit (A python wrapper for API) for building chatbots using python.


Linear Algebra, Basic matrix manipulation and vectors, NLTK, Word Embedding

Content URLs:

PyCon Singapore talk description:

Here is a link to my PyconSG presentation:

This one was a general overview of sentiment analysis, the methods and what one can do with it.

Content Slides:

Speaker Info:

I am a third year student of engineering majoring computer science. My past experience with python and NLP is of 3 years, with varied internships in Human Computer Interaction development for short texts, improved document sentiment tagger and presently interning in NTU (group Sentic Net) for personality detection and mental health disorder prediction purposes. I have previously given at talk at PyCon Singapore ( on a similar topic.

Speaker Links:

My LinkedIn profile can be viewed at:

Section: Scientific Computing
Type: Talks
Target Audience: Intermediate
Last Updated: