LEADER 13342nam 22008415 450 001 996466168003316 005 20230412112116.0 010 $a3-319-65813-1 024 7 $a10.1007/978-3-319-65813-1 035 $a(CKB)3710000001631266 035 $a(DE-He213)978-3-319-65813-1 035 $a(MiAaPQ)EBC6303273 035 $a(MiAaPQ)EBC5592675 035 $a(Au-PeEL)EBL5592675 035 $a(OCoLC)1005105744 035 $a(PPN)203850254 035 $a(EXLCZ)993710000001631266 100 $a20170816d2017 u| 0 101 0 $aeng 135 $aurnn#008mamaa 181 $ctxt$2rdacontent 182 $cc$2rdamedia 183 $acr$2rdacarrier 200 10$aExperimental IR Meets Multilinguality, Multimodality, and Interaction$b[electronic resource] $e8th International Conference of the CLEF Association, CLEF 2017, Dublin, Ireland, September 11?14, 2017, Proceedings /$fedited by Gareth J.F. Jones, Séamus Lawless, Julio Gonzalo, Liadh Kelly, Lorraine Goeuriot, Thomas Mandl, Linda Cappellato, Nicola Ferro 205 $a1st ed. 2017. 210 1$aCham :$cSpringer International Publishing :$cImprint: Springer,$d2017. 215 $a1 online resource (XVIII, 378 p. 59 illus.) 225 1 $aInformation Systems and Applications, incl. Internet/Web, and HCI ;$v10456 311 $a3-319-65812-3 327 $aIntro -- Preface -- Organization -- CLEF Steering Committee -- Contents -- Full Papers -- A Pinch of Humor for Short-Text Conversation: An Information Retrieval Approach -- 1 Introduction -- 2 Related Work -- 3 Data -- 3.1 Joke Collection -- 3.2 Yahoo!Answers -- 4 Retrieval Models -- 4.1 BM25 -- 4.2 Query Term Reweighting Model (QTR) -- 4.3 doc2vec -- 5 Evaluation -- 5.1 Yahoo!Answers -- 5.2 Lab Evaluation -- 6 Conclusion and Future Work -- References -- A Component-Level Analysis of an Academic Search Test Collection. -- 1 Introduction -- 2 Component-Level Evaluation in Academic Search -- 3 Study Configurations -- 3.1 Test Collection and Test IR System -- 3.2 Component-Level Configurations -- 3.3 Analysis Steps -- 4 Analyzing Component Performance -- 4.1 Document and Topic Structure -- 4.2 IR System Components -- 5 Conclusion -- References -- A Component-Level Analysis of an Academic Search Test Collection. -- 1 Introduction -- 2 Query Performance Prediction -- 3 Study Configurations -- 3.1 Test Collection and Test IR System -- 3.2 Analysis Steps -- 4 Analyzing Query Performance -- 4.1 Recall Base -- 4.2 Topic Specificity -- 4.3 Semantic Heterogeneity of Topic Terms -- 5 Conclusion -- References -- Improving the Reliability of Query Expansion for User-Generated Speech Retrieval Using Query Performance Prediction -- 1 Introduction -- 2 Previous Work on QE for Spoken Content -- 3 UGS Test Collection -- 3.1 UGS Document Set -- 3.2 Query and Relevance Sets -- 4 Initial Investigation of QE for UGS Retrieval -- 4.1 Retrieval Model -- 4.2 Query Expansion -- 4.3 Passage-Based QE -- 4.4 Experimental Results -- 5 Query Performance Prediction for QE -- 5.1 Query Performance Prediction Methods -- 5.2 Evaluation -- 6 Adaptive Passage-Based QE for UGS Retrieval -- 7 Conclusions and Further Studies -- References. 327 $aOptimized Convolutional Neural Network Ensembles for Medical Subfigure Classification -- 1 Introduction -- 2 Revisiting Participation at ImageCLEF 2016 -- 3 Dataset Analysis -- 3.1 Data Generation Process -- 3.2 Problems of the Dataset -- 3.3 Suggestions for Future Datasets -- 4 Methodology -- 5 Evaluation -- 5.1 Results Without Additional Images from ImageCLEF 2013 -- 5.2 Self-training Using a PubMedCentral Database Snapshot -- 6 Conclusion -- References -- IRIT-QFR: IRIT Query Feature Resource -- 1 Introduction -- 2 Query Features -- 2.1 Document Collection Independent Pre-retrieval Features: WordNet-Based and Other Linguistic Features -- 2.2 Document Collection Dependent Pre-retrieval Features -- 2.3 Post-retrieval Features -- 2.4 Collections for Which the Features Have Been Estimated -- 3 Analysis of the Resource -- 3.1 Descriptive Analysis -- 4 Applications -- 5 Conclusion -- References -- Evaluating and Improving the Extraction of Mathematical Identifier Definitions -- 1 Introduction -- 2 Related Work -- 2.1 Statistical Feature Analysis (ST) -- 2.2 Pattern Matching (PM) -- 2.3 Machine Learning -- 3 Methodology -- 3.1 Evaluation Framework -- 3.2 Evaluating Existing Approaches -- 3.3 New Machine Learning Approach (ML) -- 3.4 Evaluating the Influence of Namespaces -- 4 Results -- 5 Conclusion and Outlook -- References -- Short Papers -- Query Expansion for Sentence Retrieval Using Pseudo Relevance Feedback and Word Embedding -- 1 Introduction -- 2 Related Work -- 3 Experimental Methodology -- 4 Experimental Setup -- 5 Results and Analysis -- 6 Conclusions and Further Investigation -- References -- WebShodh: A Code Mixed Factoid Question Answering System for Web -- 1 Introduction -- 2 Related Work -- 3 Web Based Code-Mixed QA System -- 4 Evaluation Dataset and Results -- 5 Discussion and Conclusion -- References. 327 $aExtracting Graph Topological Information and Users' Opinion -- 1 Introduction -- 2 Dataset -- 3 Content and Network Analysis -- 4 Discussion -- References -- Estimating the Similarities Between Texts of Right-Handed and Left-Handed Males and Females -- Abstract -- 1 Problem Statement -- 2 Materials and Methods -- 3 Results and Discussion -- 4 Conclusion and Future Work -- Acknowledgments -- References -- Evaluation of Hierarchical Clustering via Markov Decision Processes for Efficient Navigation and Search -- 1 Introduction -- 2 Markov Decision Processes -- 2.1 Navigating a Hierarchy as an MDP -- 3 Choosing a Navigation Policy -- 3.1 Policy: Greedy Descent to Threshold Depth -- 4 Toy Example and Conclusion -- References -- Plausibility Testing for Lexical Resources -- 1 Evaluating Information System Components -- 2 Requirements for a Habitable Evaluation Scheme -- 3 Plausible Utterances -- 4 Method of Fake Sentence Generation -- 5 Swapping Strategies -- 5.1 Word Coconut -- 5.2 Sentence Coconut -- 6 Evaluating the Evaluation -- 7 Conclusion -- References -- An Improved Impostors Method for Authorship Verification -- 1 Introduction -- 2 Previous Work -- 3 The Proposed Method -- 4 Experiments -- 4.1 Setup -- 4.2 Results -- 5 Conclusion -- References -- Comparison of Character n-grams and Lexical Features on Author, Gender, and Language Variety Identification on the Same Spanish News Corpus -- 1 Introduction -- 2 Related Work -- 3 Corpus -- 4 Experimental Settings and Results -- 5 Conclusions -- References -- Enriching Existing Test Collections with OXPath -- 1 Introduction -- 2 Related Work -- 3 Materials and Methods -- 4 Results -- 5 Discussion and Conclusion -- References -- Best of the Labs -- A Highly Available Real-Time News Recommender Based on Apache Spark -- 1 Motivation -- 2 Problem Description -- 3 Related Work -- 4 Approach. 327 $a4.1 Recommender Models -- 4.2 Implementation -- 4.3 Discussion -- 5 Evaluation -- 5.1 Scalability Analysis in the Offline Evaluation Lab -- 5.2 Click-Through Rate Analysis in the Offline Evaluation Lab -- 5.3 Response Rate Analysis in the Living Lab Evaluation -- 5.4 Discussion -- 6 Conclusion -- References -- The Case for Being Average: A Mediocrity Approach to Style Masking and Author Obfuscation -- 1 Introduction -- 2 Related Work -- 3 Our Mediocrity Approach to Style Masking and Author Obfuscation -- 3.1 Calculating Text Metrics -- 3.2 Modulizing the Text -- 3.3 Text Transformations -- 3.4 Noise -- 3.5 General Transformations -- 3.6 Other Methods -- 3.7 Transformation Magnitude -- 4 Evaluation -- 5 Conclusion and Future Work -- References -- Author Clustering with an Adaptive Threshold -- Abstract -- 1 Introduction -- 2 Related Work -- 3 Test Collections and Evaluation Methodology -- 4 Simple Clustering Algorithm -- 5 Evaluation -- 6 Sensibility Assessment -- 7 Adaptive Thresholding -- 8 Conclusion -- Acknowledgments -- References -- Segmenting Compound Biomedical Figures into Their Constituent Panels -- 1 Introduction -- 2 Methods -- 3 Experiments and Results -- 3.1 Experiments -- 3.2 Datasets and Evaluation -- 3.3 Results -- 4 Conclusion -- References -- An Analysis of Cross-Genre and In-Genre Performance for Author Profiling in Social Media -- 1 Introduction and Background -- 2 GronUP -- 2.1 Preprocessing -- 2.2 Classifier -- 2.3 Features -- 3 Experiments -- 3.1 Datasets -- 3.2 Experimental Settings -- 4 Results -- 5 Analysis -- 6 Conclusions -- References -- TimeLine Illustration Based on Microblogs: When Diversification Meets Metadata Re-ranking -- 1 Introduction -- 2 Description of the Task -- 3 Related Work -- 4 Description of the Approach -- 4.1 Pre-processing of the Official Tweet Corpus -- 4.2 Content-Based Matching. 327 $a4.3 Diversification -- 4.4 Re-ranking -- 5 Experimental Results -- 5.1 Dataset -- 5.2 Parameters Settings -- 5.3 Runs Submitted -- 6 Evaluation Results -- 6.1 Classical IR Metrics -- 6.2 Informativeness -- 7 Discussion -- 7.1 Evaluation of Tweet Retrieval -- 7.2 Building a Tweet Retrieval Benchmark -- 8 Conclusion -- References -- Labs Overviews -- CLEF 2017 NewsREEL Overview: A Stream-Based Recommender Task for Evaluation and Education -- 1 Introduction -- 2 Related Work -- 2.1 Evaluation of News Recommendation Systems -- 2.2 Education -- 3 News Recommendation Scenario -- 3.1 NewsREEL Live -- 3.2 NewsREEL Replay -- 3.3 Summary -- 4 NewsREEL for Learning and Teaching -- 4.1 Participant's Perspective -- 4.2 An Instructor's Perspective -- 4.3 Summary -- 5 Conclusion and Outlook -- References -- LifeCLEF 2017 Lab Overview: Multimedia Species Identification Challenges -- 1 LifeCLEF Lab Overview -- 2 Task1: PlantCLEF -- 2.1 Dataset and Evaluation Protocol -- 2.2 Participants and Results -- 3 Task2: BirdCLEF -- 3.1 Data and Task Description -- 3.2 Participants and Results -- 4 Task3: SeaCLEF -- 4.1 Data and Task Description -- 4.2 Participants and Results -- 5 Conclusions and Perspectives -- References -- Overview of PAN'17 -- 1 Introduction -- 2 Author Identification -- 2.1 Style Breach Detection -- 2.2 Author Clustering -- 3 Author Profiling -- 3.1 Evaluation Framework -- 3.2 Results -- 4 Author Obfuscation -- 4.1 Evaluation Datasets -- 4.2 Performance Measures -- 4.3 Results -- 5 Summary -- References -- CLEF 2017 eHealth Evaluation Lab Overview -- 1 Introduction -- 2 Materials and Methods -- 2.1 Text Documents -- 2.2 Human Annotations, Queries, and Relevance Assessments -- 2.3 Evaluation Methods -- 3 Results -- 4 Conclusions -- References -- CLEF 2017 Microblog Cultural Contextualization Lab Overview. 327 $a1 Introduction: From Microblog to Cultural Contextualization. 330 $aThis book constitutes the refereed proceedings of the 8th International Conference of the CLEF Initiative, CLEF 2017, held in Dublin, Ireland, in September 2017. The 7 full papers and 9 short papers presented together with 6 best of the labs papers were carefully reviewed and selected from 38 submissions. In addition, this volume contains the results of 10 benchmarking labs reporting their year long activities in overview talks and lab sessions. The papers address all aspects of information access in any modality and language and cover a broad range of topics in the field of multilingual and multimodal information access evaluation. 410 0$aInformation Systems and Applications, incl. Internet/Web, and HCI ;$v10456 606 $aNatural language processing (Computer science) 606 $aInformation storage and retrieval systems 606 $aData mining 606 $aApplication software 606 $aArtificial intelligence 606 $aNatural Language Processing (NLP) 606 $aInformation Storage and Retrieval 606 $aData Mining and Knowledge Discovery 606 $aComputer and Information Systems Applications 606 $aArtificial Intelligence 615 0$aNatural language processing (Computer science). 615 0$aInformation storage and retrieval systems. 615 0$aData mining. 615 0$aApplication software. 615 0$aArtificial intelligence. 615 14$aNatural Language Processing (NLP). 615 24$aInformation Storage and Retrieval. 615 24$aData Mining and Knowledge Discovery. 615 24$aComputer and Information Systems Applications. 615 24$aArtificial Intelligence. 676 $a025.04 702 $aJones$b Gareth J.F$4edt$4http://id.loc.gov/vocabulary/relators/edt 702 $aLawless$b Séamus$4edt$4http://id.loc.gov/vocabulary/relators/edt 702 $aGonzalo$b Julio$4edt$4http://id.loc.gov/vocabulary/relators/edt 702 $aKelly$b Liadh$4edt$4http://id.loc.gov/vocabulary/relators/edt 702 $aGoeuriot$b Lorraine$4edt$4http://id.loc.gov/vocabulary/relators/edt 702 $aMandl$b Thomas$4edt$4http://id.loc.gov/vocabulary/relators/edt 702 $aCappellato$b Linda$4edt$4http://id.loc.gov/vocabulary/relators/edt 702 $aFerro$b Nicola$4edt$4http://id.loc.gov/vocabulary/relators/edt 801 0$bMiAaPQ 801 1$bMiAaPQ 801 2$bMiAaPQ 906 $aBOOK 912 $a996466168003316 996 $aExperimental IR Meets Multilinguality, Multimodality, and Interaction$92010759 997 $aUNISA