Page 279 - Ai Book - 10

AI Activity
AI Activity
Akinator Natural Language Processing
Akinator is a video game based on the Natural Language Processing Domain of AI.

In this game, Akinator will ask the user questions
until it guesses who or what the user has thought of.
This is a version of the “20 questions game”, where one
player can ask the other player up to 20 questions to
guess what they thought of. These questions will help
you to build important skills such as communication,
critical thinking, etc.
Let us understand with the help of few questions:
● Are you a reptile? ● Do you live in water?
● Do you have feathers? ● Do you eat meat?

In this game,Akinator will try to determine what the character, object or an animal is on the basis of
answers. To play this game online, visit the link:https://en.akinator.com/ and follow further instructions.
After playing this game, answer the following questions:

1. Were you able to guess the character?
2. If yes, in how many questions were you able to guess it?
3. If no, how many times did you try to play this game?
4. What strategy must one follow to win this game?

Stages of Project in Natural Language Processing

As you know, natural language processing refers to the ability of a computer program to understand human
language and operate accordingly. Likewise AI Project life Cycle, five stages are included in the development of a
Natural language Processing project. These stages are:
u Problem Scoping: As you read earlier, Problem scoping refers to the process of identification of a problem
and the vision to solve it. Let us understand with the help of an example. Suppose you want to create a
chatbot which can understand human language and emotions, in such a case primitive CBT technique is
required to vent out the feelings or emotions.
u Data Acquisition: You have learnt that data acquisition refers to the process of collecting data. In reference
to NLP, data acquisition refers to the process of collecting conversational data to understand the sentiments
of people so that machines can interpret the words that they use and understand their meaning. The
various means of collecting data are Surveys, Databases available on the Internet, Interviews etc.
u Data Exploration: You have learnt that data exploration is a way to get to know about data before working
with it through survey and investigation, large datasets. In reference to NLP, data exploration is a way to
clean or normalise collected data(text); e.g. removing punctuation marks, keeping minimum vocabulary so
that machine does not require grammatically correct statements but the essence of it.
u Modelling: In the modelling stage, the normalised text is being fed to an NLP based AI model. In the case of
NLP, you should always remember that data is fed to the machine only after the data pre-processing stage.
u Evaluation: In the phase of evaluation, trained model is evaluated for the relevance of answers given by
the machine to users and the accuracy for the same is generated. In the NLP evaluation stage, the answers
generated by the chatbot are compared to the actual answers.

153
153