240 likes | 514 Views
Introduction to Information Retrieval (IR), IR System, and Online IR systems. 571-Information Access and Retrieval. Class logistics. Class syllabus Textbook Readings Objectives Assignments and grading Other issues. What is Information Retrieval.
E N D
Introduction to Information Retrieval (IR), IR System, and Online IR systems 571-Information Access and Retrieval
Class logistics • Class syllabus • Textbook • Readings • Objectives • Assignments and grading • Other issues
What is Information Retrieval • Find some desired information in a store of information or database • the need to locate and obtain a particular document for which the author or title is known, usually called a known item search • the need to locate materials dealing with a particular subject or to answer a particular question, known as subject search • Key elements • Information, system, and users
Overview of 571-Information Access and Retrieval. User User Need User Behavior User Strategies User-Centered IR IR systems Components Structure Information Representation types Human-computer interaction System evaluation
IR System • A system that facilitates the matching of an individual’s information request with the information stored in the system
Examples of Information Retrieval Systems • Bibliographic IR systems • Online databases • Web search engines • OPACs • Digital libraries • Multimedia IR systems
How does an IR system work? Information sources Analysis and representation Organized information Retrieved information Matching Query analysis Analyzed queries Users
How does an IR system work? Individual User Database Producer Query Records Information Retrieval System Query Manager Program Search Parameters File Update Program Data Manager Program Database
Typical elements • The selection of documents • the conceptual analysis of documents • the organization of document representations • the storage of documents • the conceptual analysis of queries • the matching of documents and queries • the delivery of documents
Database Structure • Exact Match • Bibliographic (e.g., title) search • Best Match • Relevance • Similarity measures • probabilistic retrieval • cluster-based retrieval
Central Problems of Information Retrieval Document Representation Query Representation
Central Problems of Information Retrieval Relevance Information needs
User’s Sequence • Translating or expressing the needs • formulate a search strategy • Top-down / bottom-up • formulating a query • computer processing the query
User Need Representation • Query construction • Search strategies • Query formulation • Query re-formulation • Problems • User interfaces • Interactive search • Advanced search • General users vs. experts
Document Representation • Index • To construct representations of published items in a form suitable for inclusion in some type of database • Problems • Consistency among indexers • Terms used by author vs. indexers vs. users
Issues related to IRS Design • Information representation • organization of information • user interface • query management • data management • display of information
Issues related to IRS Use • Understand information representation and organization • understand how to represent information needs • understand how to formulate queries and evaluate results • understand how to evaluate information retrieval systems
Basic Elements of Online Industry • Database producers • Online vendors/designers/developers • Information searchers
Assignments for this week • Buy your text book, it is required! • Find a slot for your weekly presentation • Week 3 through 13 • Give three candidate weeks so I can balance • One paragraph description of your final project topic • It should be different from your weekly presentation topic