1 Information Retrieval and Extraction 資訊檢索與擷取 Chia-Hui Chang, Assistant Professor Dept. of Computer Science & Information Engineering National Central.

Slides:



Advertisements
Similar presentations
Premier Director Document Imaging
Advertisements

Dialogue – Driven Intranet Search Suma Adindla School of Computer Science & Electronic Engineering 8th LANGUAGE & COMPUTATION DAY 2009.
Natural Language and Speech Processing Creation of computational models of the understanding and the generation of natural language. Different fields coming.
Information Retrieval in Practice
T.Sharon - A.Frank 1 Internet Resources Discovery (IRD) Classic Information Retrieval (IR)
ISP 433/533 Week 2 IR Models.
Information Retrieval and Extraction -- Course Introduction Chia-Hui Chang National Central University
NaLIX: A Generic Natural Language Search Environment for XML Data Presented by: Erik Mathisen 02/12/2008.
Supervised by Prof. LYU, Rung Tsong Michael Department of Computer Science & Engineering The Chinese University of Hong Kong Prepared by: Chan Pik Wah,
Presentation Outline  Project Aims  Introduction of Digital Video Library  Introduction of Our Work  Considerations and Approach  Design and Implementation.
Modern Information Retrieval Chapter 2 Modeling. Can keywords be used to represent a document or a query? keywords as query and matching as query processing.
Basi di dati distribuite Prof. M.T. PAZIENZA a.a
Reference Collections: Task Characteristics. TREC Collection Text REtrieval Conference (TREC) –sponsored by NIST and DARPA (1992-?) Comparing approaches.
ITCS 6010 Natural Language Understanding. Natural Language Processing What is it? Studies the problems inherent in the processing and manipulation of.
Digital Library Service Integration (DLSI) --> Looking for Collections and Services to be DLSI Testbeds
Information Retrieval and Extraction 資訊檢索與擷取 Chia-Hui Chang National Central University
Information retrieval Finding relevant data using irrelevant keys Example: database of photographic images sorted by number, date. DBMS: Well structured.
Overview of Search Engines
1.3 Executing Programs. How is Computer Code Transformed into an Executable? Interpreters Compilers Hybrid systems.
Databases & Data Warehouses Chapter 3 Database Processing.
1 LOMGen: A Learning Object Metadata Generator Applied to Computer Science Terminology A. Singh, H. Boley, V.C. Bhavsar National Research Council and University.
Aurora: A Conceptual Model for Web-content Adaptation to Support the Universal Accessibility of Web-based Services Anita W. Huang, Neel Sundaresan Presented.
Some Thoughts on HPC in Natural Language Engineering Steven Bird University of Melbourne & University of Pennsylvania.
CIG Conference Norwich September 2006 AUTINDEX 1 AUTINDEX: Automatic Indexing and Classification of Texts Catherine Pease & Paul Schmidt IAI, Saarbrücken.
資訊檢索與擷取 Information Retrieval and Extraction
Chapter 2 Architecture of a Search Engine. Search Engine Architecture n A software architecture consists of software components, the interfaces provided.
WHAT IS A SEARCH ENGINE A search engine is not a physical engine, instead its an electronic code or a software programme that searches and indexes millions.
Thanks to Bill Arms, Marti Hearst Documents. Last time Size of information –Continues to grow IR an old field, goes back to the ‘40s IR iterative process.
Automatic Detection of Tags for Political Blogs Khairun-nisa Hassanali Vasileios Hatzivassiloglou The University.
Querying Structured Text in an XML Database By Xuemei Luo.
RELATIONAL FAULT TOLERANT INTERFACE TO HETEROGENEOUS DISTRIBUTED DATABASES Prof. Osama Abulnaja Afraa Khalifah
© 2001 Business & Information Systems 2/e1 Chapter 8 Personal Productivity and Problem Solving.
Lead Black Slide Powered by DeSiaMore1. 2 Chapter 8 Personal Productivity and Problem Solving.
1 Information Retrieval Acknowledgements: Dr Mounia Lalmas (QMW) Dr Joemon Jose (Glasgow)
TOPIC CENTRIC QUERY ROUTING Research Methods (CS689) 11/21/00 By Anupam Khanal.
By Chung-Hong Lee ( 李俊宏 ) Assistant Professor Dept. of Information Management Chang Jung Christian University 資料庫與資訊檢索系統的整合 - 一個文件資料庫系統的開發研究.
Distributed Information Retrieval Using a Multi-Agent System and The Role of Logic Programming.
Search Engines. Search Strategies Define the search topic(s) and break it down into its component parts What terms, words or phrases do you use to describe.
5 - 1 Copyright © 2006, The McGraw-Hill Companies, Inc. All rights reserved.
Introduction to Digital Libraries hussein suleman uct cs honours 2003.
Mining Topic-Specific Concepts and Definitions on the Web Bing Liu, etc KDD03 CS591CXZ CS591CXZ Web mining: Lexical relationship mining.
Search Engine Architecture
Collocations and Information Management Applications Gregor Erbach Saarland University Saarbrücken.
DATABASE MANAGEMENT SYSTEMS CMAM301. Introduction to database management systems  What is Database?  What is Database Systems?  Types of Database.
Database Environment Chapter 2. Data Independence Sometimes the way data are physically organized depends on the requirements of the application. Result:
Next Generation Search Engines Ehsun Daroodi 1 Feb, 2003.
1. 2 Preface In the time since the 1986 edition of this book, the world of compiler design has changed significantly 3.
2005/12/021 Fast Image Retrieval Using Low Frequency DCT Coefficients Dept. of Computer Engineering Tatung University Presenter: Yo-Ping Huang ( 黃有評 )
Hsin-Hsi Chen1-1 Chapter 1 Introduction Hsin-Hsi Chen (陳信希) 國立台灣大學資訊程學系.
Introduction to Information Retrieval Example of information need in the context of the world wide web: “Find all documents containing information on computer.
Information Retrieval
For Friday Finish chapter 23 Homework –Chapter 23, exercise 15.
Compiler Construction By: Muhammad Nadeem Edited By: M. Bilal Qureshi.
Ranking of Database Query Results Nitesh Maan, Arujn Saraswat, Nishant Kapoor.
DISTRIBUTED INFORMATION RETRIEVAL Lee Won Hee.
An Ontological Approach to Financial Analysis and Monitoring.
General Architecture of Retrieval Systems 1Adrienn Skrop.
Information Retrieval in Practice
Information Retrieval in Practice
Designing Cross-Language Information Retrieval System using various Techniques of Query Expansion and Indexing for Improved Performance  Hello everyone,
Search Engine Architecture
Introduction Multimedia initial focus
Kenneth Baclawski et. al. PSB /11/7 Sa-Im Shin
Search Engine Architecture
Datamining : Refers to extracting or mining knowledge from large amounts of data Applications : Market Analysis Fraud Detection Customer Retention Production.
Multimedia Information Retrieval
Thanks to Bill Arms, Marti Hearst
CSE 635 Multimedia Information Retrieval
Search Engine Architecture
Information Retrieval and Web Design
Presentation transcript:

1 Information Retrieval and Extraction 資訊檢索與擷取 Chia-Hui Chang, Assistant Professor Dept. of Computer Science & Information Engineering National Central University, Taiwan

2 Information Retrieval l generic information retrieval system select and return to the user desired documents from a large set of documents in accordance with criteria specified by the user l functions »document search the selection of documents from an existing collection of documents »document routing the dissemination of incoming documents to appropriate users on the basis of user interest profiles

3 Detection Need l Definition a set of criteria specified by the user which describes the kind of information desired. »queries in document search task »profiles in routing task l forms »keywords »keywords with Boolean operators »free text »example documents »...

4 Example Tipster Topic Description Number: 033 Domain: Science and Technology Topic: Companies Capable of Producing Document Management Description: Document must identify a company who has the capability to produce document management system by obtaining a turnkey- system or by obtaining and integrating the basic components. Narrative: To be relevant, the document must identify a turnkey document management system or components which could be integrated to form a document management system and the name of either the company developing the system or the company using the system. These components are: a computer, image scanner or optical character recognition system, and an information retrieval or text management system.

5 Example (Continued) Concepts: 1. document management, document processing, office automation electronic imaging 2. image scanner, optical character recognition (OCR) 3. text management, text retrieval, text database 4. optical disk Factors: Definitions Document Management-The creation, storage and retrieval of documents containing, text, images, and graphics. Image Scanner-A device that converts a printed image into a video image, without recognizing the actual content of the text or pictures. Optical Disk-A disk that is written and read by light, and are sometimes associated with the storage of digital images because of their high storage capacity.

6 search vs. routing l The search process matches a single Detection Need against the stored corpus to return a subset of documents. l Routing matches a single document against a group of Profiles to determine which users are interested in the document. l Profiles stand long-term expressions of user needs. l Search queries are ad hoc in nature. l A generic detection architecture can be used for both the search and routing.

7 Search l retrieval of desired documents from an existing corpus l Retrospective search is frequently interactive. l Methods »indexing the corpus by keyword, stem and/or phrase »apply statistical and/or learning techniques to better understand the content of the corpus »analyze free text Detection Needs to compare with the indexed corpus or a single document »...

8 Document Detection: Search

9 Document Detection: Search ( Continued ) l Document Corpus »the content of the corpus may have significant the performance in some applications l Preprocessing of Document Corpus »stemming »a list of stop words »phrases, multi-term items »...

10 Document Detection: Search ( Continued ) l Building Index from Stems »key place for optimizing run-time performance »cost to build the index for a large corpus l Document Index »a list of terms, stems, phrases, etc. »frequency of terms in the document and corpus »frequency of the co-occurrence of terms within the corpus »index may be as large as the original document corpus

11 Document Detection: Search ( Continued ) l Detection Need »the user’s criteria for a relevant document l Convert Detection Need to System Specific Query »first transformed into a detection query, and then a retrieval query. »detection query: specific to the retrieval engine, but independent of the corpus »retrieval query: specific to the retrieval engine, and to the corpus

12 Document Detection: Search ( Continued ) l Compare Query with Index l Resultant Rank Ordered List of Documents »Return the top ‘N’ documents »Rank the list of relevant documents from the most relevant to the query to the least relevant

13 Routing

14 Routing ( Continued ) l Profile of Multiple Detection Needs »A Profile is a group of individual Detection Needs that describes a user’s areas of interest. »All Profiles will be compared to each incoming document (via the Profile index). »If a document matches a Profile the user is notified about the existence of a relevant document.

15 Routing ( Continued ) l Convert Detection Need to System Specific Query l Building Index from Queries »similar to build the corpus index for searching »the quantify of source data (Profiles) is usually much less than a document corpus »Profiles may have more specific, structured data in the form of SGML tagged fields

16 Routing ( Continued ) l Routing Profile Index »The index will be system specific and will make use of all the preprocessing techniques employed by a particular detection system. l Document to be routed »A stream of incoming documents is handled one at a time to determine where each should be directed. »Routing implementation may handle multiple document streams and multiple Profiles.

17 Routing ( Continued ) l Preprocessing of Document »A document is preprocessed in the same manner that a query would be set-up in a search »The document and query roles are reversed compared with the search process l Compare Document with Index »Identify which Profiles are relevant to the document »Given a document, which of the indexed profiles match it?

18 Routing ( Continued ) l Resultant List of Profiles »The list of Profiles identify which user should receive the document

19 Summary l Generate a representation of the meaning or content of each object based on its description. l Generate a representation of the meaning of the information need. l Compare these two representations to select those objects that are most likely to match the information need.

20 DocumentsQueries Document Representation Query Representation Comparison Basic Architecture of an Information Retrieval System

21 Research Issues l Given a set of description for objects in the collection and a description of an information need, we must consider l Issue 1 »What makes a good document representation? »How can a representation be generated from a description of the document? »What are retrievable units and how are they organized?

22 Research Issues ( Continued ) l Issue 2 How can we represent the information need and how can we acquire this representation? »from a description of the information need or »through interaction with the user? l Issue 3 How can we compare representations to judge likelihood that a document matches an information need? l Issue 4 How can we evaluate the effectiveness of the retrieval process?

23 Information Extraction l Generic Information Extraction System An information extraction system is a cascade of transducers or modules that at each step add structure and often lose information, hopefully irrelevant, by applying rules that are acquired manually and/or automatically.

24 Information Extraction ( Continued ) l What are the transducers or modules? l What are their input and output? l What structure is added? l What information is lost? l What is the form of the rules? l How are the rules applied? l How are the rules acquired?

25 Example: Parser l Transducer: parser l Input: the sequence of words or lexical items l Output: a parse tree l Information added: predicate-argument and modification relations l Information lost: no l Rule form: unification grammars l Application method: chart parser l Acquisition method: manually

26 Modules l Text Zoner turn a text into a set of text segments l Preprocessor turn a text or text segment into a sequence of sentences, each of which is a sequence of lexical items, where a lexical item is a word together with its lexical attributes l Filter turn a set of sentences into a smaller set of sentences by filtering out the irrelevant ones l Preparser take a sequence of lexical items and try to identify various reliably determinable, small-scale structures

27 Modules (Continued) l Parser input a sequence of lexical items and perhaps small- scale structures (phrases) and output a set of parse tree fragments, possibly complete l Fragment Combiner turn a set of parse tree or logical form fragments into a parse tree or logical form for the whole sentence l Semantic Interpreter generate a semantic structure or logical form from a parse tree or from parse tree fragments

28 Modules (Continued) l Lexical Disambiguation turn a semantic structure with general or ambiguous predicates into a semantic structure with specific, unambiguous predicates l Coreference Resolution, or Discourse Processing turn a tree-like structure into a network-like structure by identifying different descriptions of the same entity in different parts of the text l Template Generator derive the templates from the semantic structures