Amati / Carpineto / Romano Advances in Information Retrieval

29th European Conference on IR Research, ECIR 2007, Rome, Italy, April 2-5, 2007, Proceedings
2007
ISBN: 978-3-540-71496-5
Verlag: Springer Berlin Heidelberg
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, 779 Seiten

Reihe: Information Systems and Applications, incl. Internet/Web, and HCI

This book constitutes the refereed proceedings of the 29th annual European Conference on Information Retrieval Research, ECIR 2007, held in Rome, Italy in April 2007.

The 42 revised full papers and 19 revised short papers presented together with 3 keynote talks and 21 poster papers were carefully reviewed and selected from 220 article submissions and 72 poster paper submissions. The papers are organized in topical sections on theory and design, efficiency, peer-to-peer networks, result merging, queries, relevance feedback, evaluation, classification and clustering, filtering, topic identification, expert finding, XML IR, Web IR, and multimedia IR.

Written for: Researchers and professionals

Keywords: IR, Web query mining, Web search, XML retrieval, classification, clustering, collaborative Web searches, collaborative filtering, cross-language retrieval, distributed IR, document retrieval, image retrieval, information extraction, information retrieval, multimedia retrieval, question answering, results merging, semantic orientation, similarity search, text mining

Autoren/Hrsg.

Amati, Giambattista

Carpineto, Claudio

Romano, Giovanni

Inhaltsverzeichnis

1;Preface;6
2;Organization;8
3;Table of Contents;14
4;The Next Generation Web Search and the Demise of the Classic IR Model;21
5;The Last Half-Century: A Perspective on Experimentation in Information Retrieval;22
6;Learning in Hyperlinked Environments;23
7;A Parameterised Search System;24
8;Similarity Measures for Short Segments of Text;36
9;Multinomial Randomness Models for Retrieval with Document Fields;48
10;On Score Distributions and Relevance;60
11;Modeling Term Associations for Ad-Hoc Retrieval Performance Within Language Modeling Framework;72
12;Static Pruning of Terms in Inverted Files;84
13;Efficient Indexing of Versioned Document Sequences;96
14;Light Syntactically-Based Index Pruning for Information Retrieval;108
15;Sorting Out the Document Identifier Assignment Problem;121
16;Efficient Construction of FM-index Using Overlapping Block Processing for Large Scale Texts;133
17;Performance Comparison of Clustered and Replicated Information Retrieval Systems;144
18;A Study of a Weighting Scheme for Information Retrieval in Hierarchical Peer-to-Peer Networks;156
19;A Decision-Theoretic Model for Decentralised Query Routing in Hierarchical Peer-to-Peer Networks;168
19.7;Conclusion and Outlook;178
20;Central-Rank-Based Collection Selection in Uncooperative Distributed Information Retrieval;180
21;Results Merging Algorithm Using Multiple Regression Models;193
22;Segmentation of Search Engine Results for Effective Data-Fusion;205
23;Query Hardness Estimation Using Jensen-Shannon Divergence Among Multiple Scoring Functions;218
24;Query Reformulation and Refinement Using NLP-Based Sentence Clustering;230
25;Automatic Morphological Query Expansion Using Analogy-Based Machine Learning;242
26;Advanced Structural Representations for Question Classification and Answer Re-ranking;254
27;Incorporating Diversity and Density in Active Learning for Relevance Feedback;266
28;Relevance Feedback Using Weight Propagation Compared with Information-Theoretic Query Expansion;278
29;A Retrieval Evaluation Methodology for Incomplete Relevance Assessments;291
30;Evaluating Query-Independent Object Features for Relevancy Prediction;303
31;The Utility of Information Extraction in the Classification of Books;315
32;Combined Syntactic and Semantic Kernels for Text Classification;327
33;Fast Large-Scale Spectral Clustering by Sequential Shrinkage Optimization;339
34;A Probabilistic Model for Clustering Text Documents with Multiple Fields;351
35;Personalized Communities in a Distributed Recommender System;363
36;Information Recovery and Discovery in Collaborative Web Search;376
37;Collaborative Filtering Based on Transitive Correlations Between Items;388
38;Entropy-Based Authorship Search in Large Document Collections;401
39;Use of Topicality and Information Measures to Improve Document Representation for Story Link Detection;413
40;Ad Hoc Retrieval of Documents with Topical Opinion;425
41;Probabilistic Models for Expert Finding;438
42;Using Relevance Feedback in Expert Search;451
43;Using Topic Shifts for Focussed Access to XML Repositories;464
44;Feature- and Query-Based Table of ContentsGeneration for XML Documents;476
45;Setting Per-field NormalisationHyper-parameters for the Named-Page FindingSearch Task;488
46;Combining Evidence for Relevance Criteria: A Framework and Experiments in Web Retrieval;501
47;Classifier Fusion for SVM-Based Multimedia Semantic Indexing;514
48;Search of Spoken Documents Retrieves Well Recognized Transcripts;525
49;Natural Language Processing for Usage Based Indexing of Web Resources;537
50;Harnessing Trust in Social Search;545
51;How to Compare Bilingual to Monolingual Cross-Language Information Retrieval;553
52;Multilingual Text Classification Using Ontologies;561
53;Using Visual-Textual Mutual Information and Entropy for Inter-modal Document Indexing;569
54;A Study of Global Inference Algorithms in Multi-document Summarization;577
55;Document Representation Using Global Association Distance Model;585
56;Sentence Level Sentiment Analysis in the Presence of Conjuncts Using Linguistic Analysis;593
57;PageRank: When Order Changes;601
58;Model Tree Learning for Query TermWeighting in Question Answering;609
59;Examining Repetition in User Search Behavior;617
60;Popularity Weighted Ranking for Academic Digital Libraries;625
61;Naming Functions for the Vector Space Model;633
62;Effective Use of Semantic Structure in XML Retrieval;641
63;Searching Documents Based on Relevance and Type;649
64;Investigation of the Effectiveness of Cross-Media Indexing;657
65;Improve Ranking by Using Image Information;665
66;N-Step PageRank for Web Search;673
67;Authorship Attribution Via Combination of Evidence;681
68;Cross-Document Entity Tracking;690
69;Enterprise People and Skill Discovery Using Tolerant Retrieval and Visualization;694
70;Experimental Results of the Signal Processing Approach to Distributional Clustering of Terms on Reuters-21578 Collection;698
71;Overall Comparison at the Standard Levels of Recall of Multiple Retrieval Methods with the Friedman Test;702
72;Building a Desktop Search Test-Bed;706
73;Hierarchical Browsing of Video Key Frames;711
74;Active Learning with History-Based Query Selection for Text Categorisation;715
75;Fighting Link Spam with a Two-Stage Ranking Strategy;719
76;Improving Naive Bayes Text Classifier Using Smoothing Methods;723
77;Term Selection and Query Operations for Video Retrieval;728
78;An Effective Threshold-Based Neighbor Selection in Collaborative Filtering;732
79;Combining Multiple Sources of Evidence in XML Multimedia Documents: An Inference Network Incorporating Element Language Models;736
80;Language Model Based Query Classification;740
81;Integration of Text and Audio Features for Genre Classification in Music Information;744
82;Retrieval Method for Video Content in Different Format Based on Spatiotemporal Features;748
83;Combination of Document Priors in Web Information Retrieval;752
84;Enhancing Expert Search Through Query Modeling;757
85;A Hierarchical Consensus Architecture for Robust Document Clustering;761
86;Summarisation and Novelty: An Experimental Investigation;765
87;A Layered Approach to Context-Dependent User Modelling;769
88;A Bayesian Approach for Learning Document Type Relevance;773
89;Author Index;777

Leseproben

The Next Generation Web Search and the Demise of the Classic IR Model (p. 19)
Abstract. The classic IR model assumes a human engaged in activity that generates an "information need". This need is verbalized and then expressed as a query to search engine over a defined corpus. In the past decade, Web search engines have evolved from a first generation based on classic IR algorithms scaled to web size and thus supporting only informational queries, to a second generation supporting navigational queries using web specific information (primarily link analysis), to a third generation enabling transactional and other "semantic" queries based on a variety of technologies aimed to directly satisfy the unexpressed "user intent", thus moving further and further away from the classic model.

What is coming next? In this talk, we identify two trends, both representing "short-circuits" of the model: The first is the trend towards context driven Information Supply (IS), that is, the goal of Web IR will widen to include the supply of relevant information from multiple sources without requiring the user to make an explicit query. The information supply concept greatly precedes information retrieval, what is new in the web framework, is the ability to supply relevant information specific to a given activity and a given user, while the activity is being performed.

Thus the entire verbalization and query-formation phase are eliminated. The second trend is "social search" driven by the fact that the Web has evolved to being simultaneously a huge repository of knowledge and a vast social environment. As such, it is often more e.ective to ask the members of a given web milieu rather than construct elaborate queries. This short-circuits only the query formulation, but allows information finding activities such as opinion elicitation and discovery of social norms, that are not expressible at all as queries against a fixed corpus.

The Last Half-Century: A Perspective on Experimentation in Information Retrieval

Abstract. The experimental evaluation of information retrieval systems has a venerable history. Long before the current notion of a search engine, in fact before search by computer was even feasible, people in the library and information science community were beginning to tackle the evaluation issue. Sometimes it feels as though evaluation methodology has become fixed (stable or frozen, according to your viewpoint). However, this is far from the case. Interest in methodological questions is as great now as it ever was, and new ideas are continuing to develop. This talk will be a personal take on the field.

Learning in Hyperlinked Environments

Abstract. A remarkable number of important problems in different domains (e.g. web mining, pattern recognition, biology . . . ) are naturally modeled by functions de.ned on graphical domains, rather than on traditional vector spaces. Following the recent developments in statistical relational learning, in this talk, I introduce Diffusion Learning Machines (DLM) whose computation is very much related to Web ranking schemes based on link analysis. Using arguments from function approximation theory, I argue that, as a matter of fact, DLM can compute any conceivable ranking function on the Web.