ARTIFICIAL INTELLIGENCE

UNIT-05

Ms. Neha Yadav

Assistant Professor
Applied Computational Science & Engineering
Information retrieval
 Information Retrieval (IR) can be defined as a software program that deals with the
organization, storage, retrieval, and evaluation of information from document
repositories, particularly textual information.
 The main goal of IR research is to develop a model for retrieving information from
the repositories of documents.
 In ad-hoc retrieval, the user must enter a query in natural language that describes
the required information. Then the IR system will return the required documents
related to the desired information.
 IR is widely used in popular search engine like google, yahoo, bing etc.
 Characteristics:
• A huge data/document collection
• A format of query with standard query language
• The generated result model
• Displaying results model
Information extraction
 Information extraction is the task of automatically
extracting structured information from unstructured and/or
semi-structured machine-readable documents and other
electronically represented sources.
 In most of the cases this activity concerns processing human
language texts by means of natural language processing.
 One of the most trivial examples is when your email extracts
only the data from the message for you to add in your
Calendar.
 The instance of weather report with temperature, wind,
speed, humidity are extracted.
 Natural language processing
• NLP stands for Natural Language Processing, which is a
part of Computer Science, Human language, and Artificial
Intelligence.
• It is the technology that is used by machines to understand,
analyse, manipulate, and interpret human's languages.
• It helps developers to organize knowledge for performing
tasks such as translation, automatic summarization, Named
Entity Recognition (NER), speech recognition, and topic
segmentation.
Natural language processing
Advantages of NLP
 NLP helps users to ask questions about any subject and
get a direct response within seconds.
 NLP offers exact answers to the question means it does
not offer unnecessary and unwanted information.
 NLP helps computers to communicate with humans in
their languages.
 It is very time efficient.
Disdvantages of NLP
• NLP may not show context.
• NLP is unpredictable
• NLP may require more keystrokes.
• NLP is unable to adapt to the new domain, and it has a
limited function that's why NLP is built for a single and
specific task only.
NLU vs NLG
NLU(Natural language
understanding)
NLU is the process of reading and
interpretinglanguage.
It produces non-linguistic outputs from
natural language inputs.
NLG(Natural language Generating)
NLG is the process of writing or
generating language.
It produces constructing natural
language outputs from non-linguistic
inputs.
Applications of NLP
• Machine Translation
• Sentiment analysis
• Spelling correction
• Spam Detection
• Speech Recognition
• Chatbot
Role of NLP and Phases
• NLP help to communicate with intelligent system.
• Helps to control computer with voice commands.
• Helps human to communicate with machines.
• Phases:
 Lexical Analysis
 Syntactic Analysis
 Semantic Analysis
 Discourse Integration
 Pragmatic Analysis
Phases
1. Lexical Analysis:
•This is the first phase of NLP. this phase scans the source code
as a stream of characters and converts it into meaningful
lexemens. it divides the whole text into pharagraphs, sentences
and words.
2. Syntactic Analysis:
• It is used to check grammar, word arrangements, and shows
the relationship among the words.
• Example: Mumbai goes to the Delhi.
• In the real world, Agra goes to the Poonam, does not make
any sense, so this sentence is rejected by the Syntactic analyzer.
Phases
3. Semantic Analysis:
• Concerned with the meaning representation. It mainly focuses
on the literal meaning of words, phrases, and sentences.
4. Discourse Integration:
• It depends upon the sentences that proceeds it and also invokes
the meaning of the sentences that follow it.
5. Pragmatic Analysis:
• Pragmatic is the fifth and last phase of NLP. It helps you to
discover the intended effect by applying a set of rules that
characterize cooperative dialogues.
• For Example: "Open the door" is interpreted as a request instead
of an order.
Machine translation
• Machine translation is the process of using artificial
intelligence to automatically translate text from one
language to another without human involvement.
• Modern machine translation goes beyond simple word-
to-word translation to communicate the full meaning of
the original language text in the target language.
• Types of MT Systems:
• Bilingual MT System: translation between two
languages.
• Multilingual MT System: more than two languages.
Approaches for machine translation
Direct MT Approach
Interlingua Approach
Transfer Approach
Empirical MT Approach
Approaches for machine translation
Direct MT Approach:
• It is less popular but the oldest approach of MT.
• SL(source language) to TL(directly)(target
language).
Interlingua Approach:
• SL to IL(intermediate language) called
Interlingua
• Then translate IL to TL.
Approaches for machine translation
Transfer Approach:
• 1st----> SL texts to abstract SL-oriented representations.
• 2nd--> SL-oriented representations to equivalent TL-
oriented representations.
• 3rd---> Final text is generated.
Empirical MT Approach:
• This is an emerging approach for MT.
• It uses large amount of data.
• Raw data consists of the text and their translations.
• Analogy-based, example-based, memory machine translation
techniques use empirical MT approach.
Process of machine Translation
 Speech recognition
Speech Recognition is the process that enables a computer
to recognize and respond to its spoken words and then
convert them in a format that the machine understands.
Speech recognition is widely used in digital assistants,
smart speaker, smart homes and automation for a variety of
services, products and solutions.
Algorithms for Speech recognition
• Natural language processing (NLP)
• Hidden Markov models
• Markov chain model is useful for observable events such as text
inputs.
• Hidden Markov models allow us to incorporate hidden events,
such as part of speech tags into a probabilistic model.
• Neural networks
• A neural network is a series of algorithms that endeavors to
recognize underlying relationships in a set of data through a
process that mimics the way the human brain operates.
• In this sense, neural networks refer to systems of neurons,
either organic or artificial in nature.
Applications of Speech recognition
• Automotive
• Technology
• Healthcare
• Sale
• Security
ROBOT
Robot
• Robot are the artificial agents acting in real world
environment.
• Robots are aimed at manipulating the objects by
perceiving moving and doing repetitive functions without
getting bored, distracted.
Robotics
Robotics is a branch of AI which is composed of electrical
engineering, mechanical engineering and computer
science for designing, construction and application of
robots.
Robot Categories
• Manipulators (robot arms)
• Anchored to work space (factory / space station)
• Manipulable joints (turn or bend):Widely used in
manufacturing, growing in medicine.
• Mobile robots :Used for loading docks in Australia
• Mars exploration rovers
• Unmanned air vehicles (UAVs)
Robot Categories
• Mobile Manipulator
• Robots that can move in environment & interact
with it
• Must cope with the real world
• Uncertain sensing
• Uncertain locations
• Uncertain actions
Robot Hardware - Sensors
• Passive
• Cameras - capture observations
• Active
• Sonar, laser range finders - actively probe
• GPS
Robot Hardware - Effectors
Means of manipulating robot & environment
Effectors have degrees of freedom (DOF)
Represent location with 3-d location & 3 rotations
ROBOTIC PERCEPTION
 Perception is the process by which robots map sensor
measurements into internal representations of the environment. 
 Perception is difficult because sensors are noisy, and the
environment is partially observable, unpredictable, and often
dynamic
 In other words, robots have all the problems of state estimation (or
filtering)As a rule of thumb, good internal representations for
robots have three properties: They contain enough information for
the robot to make good decisions, They are structured so that they
can be updated efficiently.
 They are natural in the sense that internal variables correspond to
natural state variables in the physical world
PLANNING TO MOVE
 All of a robot’s deliberations ultimately come down to deciding how to move
effectors. The point-to-point motion problem is to deliver the robot or its end effector
to a designated target location. 
 A greater challenge is the compliant motion problem, in which a robot moves while
being in physical contact with an obstacle. An example of compliant motion is a
robot manipulator that screws in a light bulb, or a robot that pushes a box across a
table top.
 Configuration space—the space of robot states defined by location, orientation, and
joint angles—is a better place to work than the original 3D space. The path planning
problem is to find a path from one configuration to another in configuration space.
 There are two main approaches:
 cell decomposition 
 skeletonization.
MOVING
 So far, we have talked about how to plan motions, but not about
how to move. Our plans— particularly those produced by
deterministic path planners—assume that the robot can simply
follow any path that the algorithm produces.
Dynamics and control :The notion of dynamic state, which extends
the kinematic state of a robot by its velocity.For example, in
addition to the angle of a robot joint, the dynamic state also
captures the rate of change of the angle, and possibly even its
momentary acceleration.
MOVING
Potential-field control : We introduced potential fields as
an additional cost function in robot motion planning, but
they can also be used for generating robot motion directly,
dispensing with the path planning phase altogether.
To achieve this, we have to define an attractive force that
pulls the robot towards its goal configuration and a
repellent potential field that pushes the robot away from
obstacles.
Components of Robot
• Power supply
• Actuators
• Electric motors (AC/DC)
• Pneumatic air muscles
• Muscle wires
• Piezo Motors and ultrasonic motors
• Sensors.
Robot Locomotion and Types
• Locomotion is the mechanism that makes a robot
capable of moving in its environment.
• There are various types of locomotion:
1. Legged the locomotion
2. Wheeled the locomotion
3. Slip locomotion
Motion of Mobile Robot
• Terrestrial:
• Terrestrial robots move on the ground.
• Wheeled robots are most common type of robots in this category.
• Airborne
• Robotic helicopters, robotically controlled parachutes have been
deployed.
• Aquatic
• This type of robots operates in water, either at the surface or
underwater.
• Space
• Robots are designed to operate in the microgravity of outer space,
typically for space station maintenance.