The document discusses expert systems, natural language processing, and pattern recognition. It provides details on how expert systems use knowledge bases and inference engines to solve complex problems, and how natural language processing allows computers to understand human language through techniques like speech recognition and machine translation. It also gives an overview of pattern recognition and how it is used in applications like biometrics to identify and classify individuals.
3. NATURAL LANGUAGE PROCESSING
• Natural language processing (NLP) is a branch of artificial intelligence that helps computers
understand, interpret and manipulate human language. Natural Language Processing (NLP)
refers to AI method of communicating with an intelligent systems using a natural language
such as English.
• Processing of Natural Language is required when you want an intelligent system like robot to
perform as per your instructions, when you want to hear decision from a dialogue based
clinical expert system, etc.
4. • Natural language processing helps computers communicate with humans in their own language
and scales other language-related tasks. For example, NLP makes it possible for computers to
read text, hear speech, interpret it, measure sentiment and determine which parts are important.
Today’s machines can analyze more language-based data than humans, without fatigue and in a
consistent, unbiased way.
• The field of NLP involves making computers to perform useful tasks with the natural
languages humans use. The input and output of an NLP system can be −
• Speech
• Written Text
5. GOAL OF NATURAL LANGUAGE
PROCESSING
• The goal of natural language processing (NLP) is to design and build computer systems that are
able to analyze natural languages like German or English, and that generate their outputs in a
natural language, too. Typical applications of NLP are information retrieval, language
understanding, and text classification.
• Information retrieval (IR) deals with the representation, storage, organization of, and access to
information items. Given a query the goal is to extract a subset of documents from a large data
collection that satisfies a user's information need. Besides written texts the database may also
contain multimedia documents, e.g. audio and video data.
6. • In natural language understanding, the objective is to extract the meaning of an input sentence
or an input text. Usually, the meaning is represented in a suitable formal representation
language so that it can be processed by a computer.
• The goal in text classification is to assign a text document to one out of several text classes. For
newspaper articles, such classes are sports reports, finances, and politics.
7. NLPAPPLICATIONS
Text Technologies
• Spell and Grammar Checking: - Checking the spelling and the grammar of a text, and suggesting
correct alternatives for the errors.
• Text Categorization: - Assigning each text to a category.
• Information Retrieval: - Finding relevant information to the user’s query like GOOGLE, YAHOO and
BING etc.
• Summarization: - Finding the most relevant part of a document based on the user’s information need.
• Information Extraction: - Extracting the important items of a text and structuring them.
8. • Question Answering: - Answering natural language questions asked by the user.
• Machine Translation: - Translating a text from one language to another language.
• Data Fusion: - Combining extracted information from several text files into a database or an
ontology.
• Sentiment Analysis: - Identifying positive and negative opinions stated in a text.
• Optical Character Recognition: - Recognizing printed or handwritten texts and converting
them to computer-readable texts.
• Word Prediction: - Predicting the next word that is highly probable to be typed by the user.
9. Speech Technologies
• Speech Recognition: - Recognizing a spoken language and transforming it into a text.
• Speech Synthesis: - Producing a spoken language from a text.
• Spoken Dialog Systems: - Running a dialog between the user and the system.
10. Expert System
• An expert system, is an interactive computer-based decision tool that uses both facts and
heuristics to solve difficult decision making problems, based on knowledge acquired from an
expert.
• Inference engine + Knowledge = Expert system
• ( Algorithm + Data structures = Program in traditional computer )
• First expert system, called DENDRAL, was developed in the early 70's at Stanford University.
11. Application of expert system
Design Domain: Camera lens design, automobile design.
Medical Domain: Diagnosis Systems to deduce cause of disease from observed data, conduction
medical operations on humans.
Monitoring Systems: Comparing data continuously with observed system or with prescribed
behavior such as leakage monitoring in long petroleum pipeline.
Process Control Systems: Controlling a physical process based on monitoring.
Knowledge Domain: Finding out faults in vehicles, computers.
Finance/Commerce: Detection of possible fraud, suspicious transactions, stock market trading,
Airline scheduling, cargo scheduling.
12. Characteristics of Expert Systems
• High performance
• Understandable
• Reliable
• Highly responsive
14. • Client Interface processes requests for service from system-users and from application layer
components.
• Knowledge-base Editor is a simple editor that enable a subject matter expert to compose and
add rules to the Knowledge-base.
• Rule Translator converts rules from one form to another i.e; their original form to a machine-
readable form.
• Rule Engine(inference engine) is responsible for executing Knowledge-base rules.
• The shell component, Rule Object Classes, is a container for object classes supporting.
15. Components of expert system
User interface : The code that controls the dialog between the user and the system.
Knowledge base : A declarative representation of the expertise often in IF THEN rules .
Inference engine : The code at the core of the system which derives recommendations from the
knowledge base and problem specific data in working storage.
Working storage : The data which is specific to a problem being solved.
16. Advantage
Availability − They are easily available due to mass production of software.
Less Production Cost − Production cost is reasonable. This makes them affordable.
Speed − They offer great speed. They reduce the amount of work an individual puts in.
Less Error Rate − Error rate is low as compared to human errors.
Reducing Risk − They can work in the environment dangerous to humans.
Steady response − They work steadily without getting motional, tensed or fatigued.
17. Disadvantage
• Knowledge is not always readily available
• Expertise can be hard to extract from humans
• Each expert’s approach may be different, yet correct
• Hard, even for a highly skilled expert, to work under time pressure
• it work well only in a narrow domain of knowledge
18. Pattern Recognition
• Pattern recognition deals with identifying a pattern and confirming it again. In general, a
pattern can be a fingerprint image, a handwritten cursive word, a human face, a speech signal, a
bar code, or a web page on the Internet.
• The individual patterns are often grouped into various categories based on their properties.
When the patterns of same properties are grouped together, the resultant group is also a pattern,
which is often called a pattern class.
• Pattern recognition is the science for observing, distinguishing the patterns of interest, and
making correct decisions about the patterns or pattern classes. Thus, a biometric system applies
pattern recognition to identify and classify the individuals, by comparing it with the stored
templates.
19. Pattern Recognition in Biometrics
The pattern recognition technique conducts the following tasks −
Classification − Identifying handwritten characters, CAPTCHAs, distinguishing humans from
computers.
Segmentation − Detecting text regions or face regions in images.
Syntactic Pattern Recognition − Determining how a group of math symbols or operators are
related, and how they form a meaningful expression.