Information retrieval 15 alternative algebraic models

Jun 10, 2020Download as PPTX, PDF0 likes381 views

The document discusses alternative algebraic models for information retrieval, including the generalized vector model. The generalized vector model allows for index terms to be non-orthogonal, representing correlations between terms. It models term dependencies through "minterms" - binary patterns of term occurrence. While allowing representation of term correlations, the model has higher computational costs than the standard vector model and it is unclear when it performs better.

Information Retrieval : 15
Alternative Algebraic Models
Prof Neeraj Bhargava
Vaibhav Khanna
Department of Computer Science
School of Engineering and Systems Sciences
Maharshi Dayanand Saraswati University Ajmer

Alternative Algebraic Models
• Generalized Vector Model
• Latent Semantic Indexing
• Neural Network Model

Generalized Vector Model
• Classic models enforce independence of index
terms
• In the generalized vector space model, two
index term vectors might be non-orthogonal

Key Idea
• As before, let wi,j be the weight associated with [ki, dj ] and V =
{k1, k2, . . ., kt} be the set of all terms
• If the wi,j weights are binary, all patterns of occurrence of
terms within docs can be represented by minterms:

Information retrieval 15 alternative algebraic models

• Pairwise orthogonality among the ~mr vectors does
not imply independence among the index terms
• On the contrary, index terms are now correlated by the
~mr vectors
– For instance, the vector ~m4 is associated with the
minterm m4 = (1, 1, . . . , 0)
– This minterm induces a dependency between terms k1
and k2
– Thus, if such document exists in a collection, we say that
the minterm m4 is active
• The model adopts the idea that co-occurrence of terms
induces dependencies among these terms

Conclusions
• Model considers correlations among index
terms
• Not clear in which situations it is superior to
the standard Vector model
• Computation costs are higher
• Model does introduce interesting new ideas

Assignment
• Explain the Generalized Vector Model of IR

The document discusses probabilistic information retrieval and Bayesian approaches. It introduces concepts like conditional probability, Bayes' theorem, and the probability ranking principle. It explains how probabilistic models estimate the probability of relevance between a document and query by representing them as term sets and making probabilistic assumptions. The goal is to rank documents by the probability of relevance to present the most likely relevant documents first.

Information retrieval 13 alternative set theoretic modelsVaibhav Khanna

Information retrieval 10 vector and probabilistic modelsVaibhav Khanna

Topic ModelingKarol Grzegorczyk

Topic modeling is a technique for discovering hidden semantic patterns in large document collections. It represents documents as probability distributions over latent topics, where each topic is characterized by a distribution over words. Two common probabilistic topic models are latent Dirichlet allocation (LDA) and probabilistic latent semantic analysis (pLSA). LDA assumes each document exhibits multiple topics in different proportions, with topics modeled as distributions over words. Topic modeling provides dimensionality reduction and can be applied to problems like text classification, collaborative filtering, and computer vision tasks like image classification.

Term weightingPrimya Tamil

The document discusses various aspects of term weighting which is important for text retrieval systems, including term frequency, document frequency, inverse document frequency, and how they are used to calculate TF-IDF weights for terms. It also covers stoplists, stemming, and the bag-of-words model which represents text as vectors of word occurrences without considering word order. Term weighting schemes play a major role in the similarity measures used by information retrieval systems to determine document relevance.

Boolean,vector space retrieval Models Primya Tamil

The document discusses various information retrieval models including Boolean, vector space, and probabilistic models. It provides details on how documents and queries are represented and compared in the vector space model. Specifically, it explains that in this model, documents and queries are represented as vectors of term weights in a multi-dimensional space. The similarity between a document and query vector is calculated using measures like the inner product or cosine similarity to retrieve and rank documents.

Vector space model of information retrievalNanthini Dominique

The document discusses different theories used in information retrieval systems. It describes cognitive or user-centered theories that model human information behavior and structural or system-centered theories like the vector space model. The vector space model represents documents and queries as vectors of term weights and compares similarities between queries and documents. It was first used in the SMART information retrieval system and involves assigning term vectors and weights to documents based on relevance.

Information retrieval 14 fuzzy set models of irVaibhav Khanna

CS6007 information retrieval - 5 units notesAnandh Arumugakan

This document provides a full syllabus with questions and answers related to the course "Information Retrieval" including definitions of key concepts, the historical development of the field, comparisons between information retrieval and web search, applications of IR, components of an IR system, and issues in IR systems. It also lists examples of open source search frameworks and performance measures for search engines.

Information retrieval introductionnimmyjans4

This document provides an overview of information retrieval models. It begins with definitions of information retrieval and how it differs from data retrieval. It then discusses the retrieval process and logical representations of documents. A taxonomy of IR models is presented including classic, structured, and browsing models. Boolean, vector, and probabilistic models are explained as examples of classic models. The document concludes with descriptions of ad-hoc retrieval and filtering tasks and formal characteristics of IR models.

Tutorial 1 (information retrieval basics)Kira

The document discusses the basics of information retrieval systems. It covers two main stages - indexing and retrieval. In the indexing stage, documents are preprocessed and stored in an index. In retrieval, queries are issued and the index is accessed to find relevant documents. The document then discusses several models for defining relevance between documents and queries, including the Boolean model and vector space model. It also covers techniques for representing documents and queries as vectors and calculating similarity between them.

Information retrieval 12 modern ir and set based modelsVaibhav Khanna

The vector space modelpkgosh

The document discusses the vector space model for representing text documents and queries in information retrieval systems. It describes how documents and queries are represented as vectors of term weights, with each term being assigned a weight based on its frequency in the document or query. The vector space model allows documents and queries to be compared by calculating the similarity between their vector representations. Terms that are more frequent in a document and less frequent overall are given higher weights through techniques like TF-IDF weighting. This vector representation enables efficient retrieval of documents ranked by similarity to the query.

The impact of web on irPrimya Tamil

The document discusses the World Wide Web and information retrieval on the web. It provides background on how the web was developed by Tim Berners-Lee in 1990 using HTML, HTTP, and URLs. It then discusses some key differences in information retrieval on the web compared to traditional library systems, including the presence of hyperlinks, heterogeneous content, duplication of content, exponential growth in the number of documents, and lack of stability. It also summarizes some challenges in web search including the expanding nature of the web, dynamically generated content, influence of monetary contributions on search results, and search engine spamming.

Evaluation in Information RetrievalDishant Ailawadi

This document discusses evaluation in information retrieval. It describes standard test collections which consist of a document collection, queries on the collection, and relevance judgments. It also discusses various evaluation measures used in information retrieval like precision, recall, F-measure, mean average precision, and kappa statistic which measure reliability of relevance judgments. R-precision and normalized discounted cumulative gain are also summarized as important single number evaluation measures.

Web search vs irPrimya Tamil

This document compares web search and information retrieval (IR) across 10 differentiators: 1. Languages - Web search indexes documents in many languages using full text, while IR databases usually cover one language. 2. File types - Web search indexes several file types including some without text, while IR indexes consistent formats like PDF. 3. Document length - Web documents vary widely in length from short to long, while IR documents vary less. 4. Document structure - Web documents are semi-structured HTML, while IR allows searching structured document fields.

Introduction to Information RetrievalRoi Blanco

Information retrieval ssilambu111

The document discusses information retrieval, which involves obtaining information resources relevant to an information need from a collection. The information retrieval process begins when a user submits a query. The system matches queries to database information, ranks objects based on relevance, and returns top results to the user. The process involves document acquisition and representation, user problem representation as queries, and searching/retrieval through matching and result retrieval.

Information Retrieval ModelsNisha Arankandath

The document discusses various information retrieval models, including: 1) Classic models like Boolean and vector space models that use index terms to represent documents and queries. 2) Probabilistic models that view IR as estimating the probability of relevance between documents and queries. 3) Structured models that incorporate document structure, including models based on non-overlapping text regions and hierarchical document structure. 4) Browsing models like flat, structure-guided, and hypertext models for navigating document collections.

Blow fish final pptAjay AJ

This document discusses the design and implementation of the Blowfish encryption algorithm using Verilog HDL. Blowfish is a symmetric block cipher that uses a variable-length key from 32 to 448 bits, making it suitable for securing data. The algorithm consists of two parts - key expansion and a round structure involving 16 rounds of operations. The authors implemented Blowfish using Verilog HDL on a Xilinx FPGA for applications requiring encryption like IoT devices. Their design achieved high-speed encryption of up to 4 bits per clock cycle and operated at a maximum frequency of 50MHz.

Information retrival system and PageRank algorithmRupali Bhatnagar

Language Models for Information RetrievalDustin Smith

The document provides background information on Christopher Manning, Prabhakar Raghavan, and Hinrich Schutze, who are authors of the book "Introduction to Information Retrieval: Language models for information retrieval". It then outlines the presentation which discusses language models for information retrieval, including query likelihood models, estimating query generation probabilities, and experiments comparing language modeling approaches to other IR techniques.

NLP_KASHK:Evaluating Language ModelHemantha Kulathilake

This document discusses methods for evaluating language models, including intrinsic and extrinsic evaluation. Intrinsic evaluation involves measuring a model's performance on a test set using metrics like perplexity, which is based on how well the model predicts the test set. Extrinsic evaluation embeds the model in an application and measures the application's performance. The document also covers techniques for dealing with unknown words like replacing low-frequency words with <UNK> and estimating its probability from training data.

Mining single dimensional boolean association rules from transactionalramya marichamy

The document discusses mining frequent itemsets and generating association rules from transactional databases. It introduces the Apriori algorithm, which uses a candidate generation-and-test approach to iteratively find frequent itemsets. Several improvements to Apriori's efficiency are also presented, such as hashing techniques, transaction reduction, and approaches that avoid candidate generation like FP-trees. The document concludes by discussing how Apriori can be applied to answer iceberg queries, a common operation in market basket analysis.

MD5 ALGORITHM.pptxRajapriya82

The MD5 algorithm is a cryptographic hash function that generates a 128-bit digest from a message of any length. It works by first padding the message to a length that is a multiple of 512 bits, then appending the message length. It initializes buffers and processes the message in 512-bit blocks using four rounds of 16 operations each, applying different functions to update the buffers. The final buffer values become the MD5 digest. It is commonly used to verify file integrity but is now considered insecure due to possible hash collisions.

PAC LearningSanghyuk Chun

This document provides an overview of PAC (Probably Approximately Correct) learning theory. It discusses how PAC learning relates the probability of successful learning to the number of training examples, complexity of the hypothesis space, and accuracy of approximating the target function. Key concepts explained include training error vs true error, overfitting, the VC dimension as a measure of hypothesis space complexity, and how PAC learning bounds can be derived for finite and infinite hypothesis spaces based on factors like the training size and VC dimension.

lecture12-clustering.pptImXaib

This document provides an introduction and overview of document clustering techniques in information retrieval. It discusses motivations for clustering documents, such as improving search recall and organizing search results. It covers common clustering algorithms like K-means and hierarchical clustering, how they work, and considerations like choosing the number of clusters. The document uses examples and diagrams to illustrate clustering concepts and algorithms.

Introduction to Information Retrieval & ModelsMounia Lalmas-Roelleke

INTRODUCTION TO INFORMATION RETRIEVAL This lecture will introduce the information retrieval problem, introduce the terminology related to IR, and provide a history of IR. In particular, the history of the web and its impact on IR will be discussed. Special attention and emphasis will be given to the concept of relevance in IR and the critical role it has played in the development of the subject. The lecture will end with a conceptual explanation of the IR process, and its relationships with other domains as well as current research developments. INFORMATION RETRIEVAL MODELS This lecture will present the models that have been used to rank documents according to their estimated relevance to user given queries, where the most relevant documents are shown ahead to those less relevant. Many of these models form the basis for many of the ranking algorithms used in many of past and today’s search applications. The lecture will describe models of IR such as Boolean retrieval, vector space, probabilistic retrieval, language models, and logical models. Relevance feedback, a technique that either implicitly or explicitly modifies user queries in light of their interaction with retrieval results, will also be discussed, as this is particularly relevant to web search and personalization.

AI to advance science researchDing Li

This document discusses how AI can help advance various scientific fields such as mathematics, quantum chemistry, biology, and more. It provides examples of how machine learning has helped mathematicians develop new theories by analyzing patterns in examples. It also discusses how AI is helping push the limits of density functional theory in quantum chemistry and how AlphaFold uses transformers and protein multiple sequence alignments to predict structures with near experimental accuracy. The conclusion emphasizes not becoming a slave to models and maintaining inspiration.

Chapter 4 IR Models.pdfHabtamu100

The document discusses information retrieval (IR) models, including the Boolean, vector space, and probabilistic models. The Boolean model represents documents and queries as sets of index terms and determines relevance through binary term presence, while the vector space model represents documents and queries as weighted vectors in a multidimensional space and ranks documents by calculating similarity between document and query vectors. The probabilistic model determines relevance probabilities based on the likelihood of terms appearing in relevant vs. non-relevant documents.

More Related Content

What's hot (20)

CS6007 information retrieval - 5 units notesAnandh Arumugakan

Information retrieval introductionnimmyjans4

Tutorial 1 (information retrieval basics)Kira

Information retrieval 12 modern ir and set based modelsVaibhav Khanna

The vector space modelpkgosh

The impact of web on irPrimya Tamil

Evaluation in Information RetrievalDishant Ailawadi

Web search vs irPrimya Tamil

Introduction to Information RetrievalRoi Blanco

Information retrieval ssilambu111

Information Retrieval ModelsNisha Arankandath

Blow fish final pptAjay AJ

Information retrival system and PageRank algorithmRupali Bhatnagar

Language Models for Information RetrievalDustin Smith

NLP_KASHK:Evaluating Language ModelHemantha Kulathilake

Mining single dimensional boolean association rules from transactionalramya marichamy

MD5 ALGORITHM.pptxRajapriya82

PAC LearningSanghyuk Chun

lecture12-clustering.pptImXaib

Introduction to Information Retrieval & ModelsMounia Lalmas-Roelleke

CS6007 information retrieval - 5 units notesAnandh Arumugakan

Information retrieval introductionnimmyjans4

Tutorial 1 (information retrieval basics)Kira

Information retrieval 12 modern ir and set based modelsVaibhav Khanna

The vector space modelpkgosh

The impact of web on irPrimya Tamil

Evaluation in Information RetrievalDishant Ailawadi

Web search vs irPrimya Tamil

Introduction to Information RetrievalRoi Blanco

Information retrieval ssilambu111

Information Retrieval ModelsNisha Arankandath

Blow fish final pptAjay AJ

Information retrival system and PageRank algorithmRupali Bhatnagar

Language Models for Information RetrievalDustin Smith

NLP_KASHK:Evaluating Language ModelHemantha Kulathilake

Mining single dimensional boolean association rules from transactionalramya marichamy

MD5 ALGORITHM.pptxRajapriya82

PAC LearningSanghyuk Chun

lecture12-clustering.pptImXaib

Introduction to Information Retrieval & ModelsMounia Lalmas-Roelleke

Similar to Information retrieval 15 alternative algebraic models (20)

AI to advance science researchDing Li

Chapter 4 IR Models.pdfHabtamu100

Information retrieval 20 divergence from randomnessVaibhav Khanna

Divergence from randomness, one of the very first models, is one type of probabilistic model. It is basically used to test the amount of information carried in the documents. It is based on Harter's 2-Poisson indexing-model. The 2-Poisson model has a hypothesis that the level of the documents is related to a set of documents which contains words occur relatively greater than the rest of the documents

Probabilistic models (part 1)KU Leuven

This document discusses probabilistic models used for text mining. It introduces mixture models, Bayesian nonparametric models, and graphical models including Bayesian networks, hidden Markov models, Markov random fields, and conditional random fields. It provides details on the general framework of mixture models and examples like topic models PLSA and LDA. It also discusses learning algorithms for probabilistic models like EM algorithm and Gibbs sampling.

Speech recognition using vector quantization through modified k means lbg alg...Alexander Decker

This document discusses speech recognition using vector quantization and proposes a modified K-meansLBG algorithm. It begins by introducing vector quantization techniques which are commonly used in speech recognition. It then describes the Linde-Buzo-Gray (LBG) algorithm and classical K-means algorithm for vector quantization before proposing a modified K-meansLBG algorithm. The paper claims this modified algorithm provides superior performance compared to the classical approaches. It evaluates the performance of the proposed algorithm through experimental work.

Presentation1Vikas Saxena

This document discusses innovative practices in teaching discrete structures/mathematics and data structures to undergraduate computer science students. It describes course structures at various universities and suggests focusing discrete mathematics on fundamental concepts like logic, proofs, and counting before more advanced topics. For data structures, it recommends teaching implementation to build understanding but also focusing on usage. Projects, multimedia, and games are presented as motivating teaching techniques. Historical sources are proposed to provide context for abstract concepts.

Bj24390398IJERA Editor

This document summarizes an academic paper that proposes an innovative modified K-Mode clustering algorithm for categorical data. The paper begins by introducing clustering algorithms and discusses existing algorithms like K-Means, K-Medoids, and K-Mode that are used for numerical and categorical data. It then describes the limitations of traditional K-Mode clustering and proposes a modified K-Mode algorithm that aims to provide better initial cluster means/modes to result in clusters with better accuracy. The paper experimentally evaluates the traditional and modified K-Mode algorithms on large datasets to compare their performance for varying data values.

OntoMаthPro Ontology: A Linked Data Hub for MathematicsAlik Kirillovich

4-IR Models_new.pptBereketAraya

The document discusses the vector space model used in information retrieval. It explains that documents and queries are represented as weighted vectors in a high dimensional vector space. Similarities between queries and documents are calculated to rank documents by relevance. Weights are often calculated using TF-IDF, which considers the frequency of terms within documents and across collections. Documents with vector representations closer to the query vector are considered more relevant.

4-IR Models_new.pptBereketAraya

The document discusses the vector space model used in information retrieval. It explains that documents and queries are represented as weighted vectors in a multidimensional space. Similar vectors are close to each other. The weights used are usually tf-idf, which considers both the frequency of a term within a document and its rarity across documents. Documents are ranked based on the similarity between their vector representation and the query vector.

DMTM 2015 - 06 Introduction to ClusteringPier Luca Lanzi

240715_JW_labseminar[metapath2vec: Scalable Representation Learning for Heter...thanhdowork

Introduction to Neural networks (under graduate course) Lecture 8 of 9Randa Elanwar

NS-CUK Seminar: H.B.Kim, Review on "metapath2vec: Scalable representation le...ssuser4b1f48

NS-CUK Seminar: H.B.Kim, Review on "metapath2vec: Scalable representation l...ssuser4b1f48

Digital Image Processing.pptxMukhtiarKhan5

QUANTIFYING THE THEORY VS. PROGRAMMING DISPARITY USING SPECTRAL BIPARTIVITY A...ijcsit

This document proposes two approaches to quantify the disparity between students' performance in theoretical versus programming assignments in computer science courses. The first approach uses spectral bipartivity analysis to partition assignments based on student scores, then calculates a Theory vs Programming Tuple Proximity distance between the partitions and actual theoretical/programming assignments to derive a Theory vs Programming Disparity metric for each student. The second approach applies principal component analysis separately to theoretical and programming assignment scores for all students, then correlates the principal components to determine a class-level disparity metric based on correlation coefficients and their variances.

Quantifying the Theory Vs. Programming Disparity using Spectral Bipartivity A...AIRCC Publishing Corporation

Some students in the Computer Science and related majors excel very well in programming-related assignments, but not equally well in the theoretical assignments (that are not programming-based) and vice-versa. We refer to this as the "Theory vs. Programming Disparity (TPD)". In this paper, we propose a spectral bipartivity analysis-based approach to quantify the TPD metric for any student in a course based on the percentage scores (considered as decimal values in the range of 0 to 1) of the student in the course assignments (that involves both theoretical and programming-based assignments). We also propose a principal component analysis (PCA)-based approach to quantify the TPD metric for the entire class based on the percentage scores (in a scale of 0 to 100) of the students in the theoretical and programming assignments. The spectral analysis approach partitions the set of theoretical and programming assignments to two disjoint sets whose constituents are closer to each other within each set and relatively more different from each across the two sets

Av33274282IJERA Editor

International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.

Av33274282IJERA Editor

AI to advance science researchDing Li

Chapter 4 IR Models.pdfHabtamu100

Information retrieval 20 divergence from randomnessVaibhav Khanna

Probabilistic models (part 1)KU Leuven

Speech recognition using vector quantization through modified k means lbg alg...Alexander Decker

Presentation1Vikas Saxena

Bj24390398IJERA Editor

OntoMаthPro Ontology: A Linked Data Hub for MathematicsAlik Kirillovich

4-IR Models_new.pptBereketAraya

DMTM 2015 - 06 Introduction to ClusteringPier Luca Lanzi

240715_JW_labseminar[metapath2vec: Scalable Representation Learning for Heter...thanhdowork

Introduction to Neural networks (under graduate course) Lecture 8 of 9Randa Elanwar

NS-CUK Seminar: H.B.Kim, Review on "metapath2vec: Scalable representation le...ssuser4b1f48

NS-CUK Seminar: H.B.Kim, Review on "metapath2vec: Scalable representation l...ssuser4b1f48

Digital Image Processing.pptxMukhtiarKhan5

QUANTIFYING THE THEORY VS. PROGRAMMING DISPARITY USING SPECTRAL BIPARTIVITY A...ijcsit

Quantifying the Theory Vs. Programming Disparity using Spectral Bipartivity A...AIRCC Publishing Corporation

Av33274282IJERA Editor

More from Vaibhav Khanna (20)

Information and network security 47 authentication applicationsVaibhav Khanna

Information and network security 46 digital signature algorithmVaibhav Khanna

Information and network security 45 digital signature standardVaibhav Khanna

Information and network security 44 direct digital signaturesVaibhav Khanna

Information and network security 43 digital signaturesVaibhav Khanna

Information and network security 42 security of message authentication codeVaibhav Khanna

Information and network security 41 message authentication codeVaibhav Khanna

Message authentication aims to protect integrity, validate originator identity, and provide non-repudiation. It addresses threats like masquerading, content or sequence modification, and source/destination repudiation. A Message Authentication Code (MAC) provides assurance that a message is unaltered and from the sender by appending a cryptographic checksum to the message dependent on the key and content. The receiver can validate the MAC to verify integrity and authenticity.

Information and network security 40 sha3 secure hash algorithmVaibhav Khanna

Information and network security 39 secure hash algorithmVaibhav Khanna

The Secure Hash Algorithm (SHA) is a cryptographic hash function developed by the US National Security Agency. SHA-512 is the latest version that produces a 512-bit hash value. It processes message blocks of 1024 bits using an 80-step compression function that updates a 512-bit buffer. Each step uses a 64-bit value derived from the message and a round constant. SHA-512 supports messages up to 2^128 bits in length and adds between 1 and 1023 padding bits as needed.

Information and network security 38 birthday attacks and security of hash fun...Vaibhav Khanna

Information and network security 37 hash functions and message authenticationVaibhav Khanna

Information and network security 35 the chinese remainder theoremVaibhav Khanna

Information and network security 34 primalityVaibhav Khanna

Information and network security 33 rsa algorithmVaibhav Khanna

Information and network security 32 principles of public key cryptosystemsVaibhav Khanna

Information and network security 31 public key cryptographyVaibhav Khanna

Information and network security 30 random numbersVaibhav Khanna

Information and network security 29 international data encryption algorithmVaibhav Khanna

Information and network security 28 blowfishVaibhav Khanna

Information and network security 27 triple desVaibhav Khanna