Information Retrieval Overview of IR Research Information Seeking

Information Retrieval Overview of IR Research

Information Seeking Process: Dynamic, Interactive, Iterative User n What am I looking for? - Identification of info. need n What question do I ask? - Query formulation Intermediary What is the searcher looking for? - Discovery of user’s info. need n How should the question be posed? - Query representation n Where is the relevant information? - Query-document matching n n Search Engines Information What data to collect? - Collection development What information to index? - Indexing/Representation How to represent it? - Data structure 2

Information Seeking Models n Traditional Model Linear process: 1. 2. 3. 4. Interesting information is scattered like berries among bushes. Information seeking is a dynamic, nonlinear process, where information need/queries continually shift. Information needs are not satisfied by a single, final retrieved set of documents, but rather by a series of selections and bits of information found along the way. Problem identification Identification of information need Query formulation Result evaluation Static information need The goal is to retrieve a perfect match of the information need Broader, 2002 Search Engines Berry-picking Model (딸기따기 모델) n Bates, 1989 3

IR Research: Overview Information Access - Retrieve information Data Mining - Discover Knowledge Search Engines Information Retrieval - Create a searchable index Information Organization: Add structure & annotation 4

IR Research: Information Retrieval Representation - indexing, term weighting Query Formulation - “What is information retrieval? ” D 1: information retrieval seminars D 2: retrieval models and information retrieval D 3: information model Search Results - (ranked) document list Search Engines Rank doc. ID 1 D 2 2 3 score Searchable Index Raw Data Index Term D 1 D 2 D 3 D 1 wd 2 wd 3 3 wd 1 (information) 1 1 1 D 2 D 1 2 wd 2 (model) 0 1 1 wd 3 wd 2 wd 1 wd 3 D 3 1 wd 3 (retrieval) 1 2 0 D 3 wd 1 wd 2 wd 4 (seminar) 1 0 0 5

IR Research: Information Organization Query Formulation - “What is IR? ” Search Results Representation - NLP & Machine Learning Organized Data Raw Data - document groups Search Engines 6

IR Research: Natural Language Processing n Goal n Lexical Analysis using n Understanding/effective processing of natural language · Not just pattern matching Part-of-Speech (POS) tagging Sentence Parsing Research area, technique, tool for Search Engines Data Mining, Knowledge Discovery 7

IR Research: Machine Learning n Research Area, technique, tool for n Information Organization, Data Mining, Knowledge Discovery Information Organization via Supervised Learning (Automatic Classification) Unsupervised Learning (Clustering) Class 1 Class 2 Classification Class 1 Class 2 Clustering Search Engines 8