Lecture-B

Lecture-B - Lecture B IR Models Introduction s s IR systems...

Info iconThis preview shows pages 1–12. Sign up to view the full content.

View Full Document Right Arrow Icon
Lecture B IR Models
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
2 Introduction IR systems usually adopt index terms to index documents and process queries Index term: A keyword or group of selected/related words Stemming might be used, e.g., connect for connecting, connection, connections Any word (in general) An inverted file is built for the chosen index terms Problems of IR based on index terms: Oversimplication that causes lose of semantics Badly-formed queries
Background image of page 2
3 Introduction Docs Information Need query Ranking match Index Terms docs
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
4 Introduction Matching at index term level is quite imprecise Consequence: no surprise that users get frequently unsatisfied Since most users have no training in query formation, problem is even worst Result: frequent dissatisfaction of Web users Issue of deciding relevance is critical for IR systems: ranking
Background image of page 4
5 Introduction A ranking is an ordering of the retrieved documents that (hopefully) reflects the (degrees of ) relevance of the documents to the user query A ranking is based on fundamental premises regarding the notion of relevance, such as: common sets of index terms (the set-theoretical approach) sharing of weighted terms (the algebraic approach) likelihood of relevance (the probablistic approach) Each set of premises leads to a distinct IR model
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
6 IR Models Non-Overlapping Lists Proximal Nodes Structured Models Retrieval: Ad hoc Filtering Browsing U s e r T a s k Classic Models Boolean Vector (Space) Probabilistic Set Theoretic Fuzzy Extended Boolean Probabilistic Inference Network Belief Network Algebraic Generalized Vector (Space) Latent Semantic Index Neural Networks Browsing Flat Structure Guided Hypertext
Background image of page 6
7 IR Models The IR model, the logical view of the documents, and the retrieval task are distinct aspects of the system Index Terms Full Text Full Text + Structure Retrieval Classic Set Theoretic Algebraic Probabilistic Classic Set Theoretic Algebraic Probabilistic Structured Browsing Flat Flat Hypertext Structure Guided Hypertext LOGICAL VIEW OF DOCUMENTS U S E R T A S K
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
8 Retrieval: Ad Hoc vs. Filtering Ad hoc retrieval : Static set of documents and dynamic queries Collection “Fixed Size” Q2 Q3 Q1 Q4 Q5
Background image of page 8
9 Retrieval: Ad Hoc vs. Filtering Filtering : dynamic set of documents and static queries User 1 Profile User 2 Profile Documents Stream incoming Docs Filtered for User 2 Docs Filtered for User 1 outgoing outgoing
Background image of page 9

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
10 Classic IR Models – User Profiles Document Representation: Each document is described by a set of representative keywords or index terms Index terms are document words (i.e. nouns ), which have meaning by themselves for remembering the main themes of a document Full text representation : search engines assume that all words are index terms User profile construction process: 1) user-provided keywords 2) relevance feedback cycle 3) system adjusted user profile description 4) repeat step (2) till stabilized
Background image of page 10
11 Classic IR Models - Basic Concepts
Background image of page 11

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 12
This is the end of the preview. Sign up to access the rest of the document.

Page1 / 92

Lecture-B - Lecture B IR Models Introduction s s IR systems...

This preview shows document pages 1 - 12. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online