Experimental IR Meets Multilinguality, Multimodality, and Interaction

Name: Experimental IR Meets Multilinguality, Multimodality, and Interaction | 8th International Conference of the CLEF Association, CLEF 2017, Dublin, Ireland, September 11-14, 2017, Proceedings
Brand: Springer
Price: 53.49 EUR
Availability: OnlineOnly

8th International Conference of the CLEF Association, CLEF 2017, Dublin, Ireland, September 11-14, 2017, Proceedings

Gareth J.F. Jones Séamus Lawless Julio Gonzalo Liadh Kelly Lorraine Goeuriot Thomas Mandl Linda Cappellato Nicola Ferro(Herausgeber*in)

Springer (Verlag)

Erschienen am 31. August 2017

XVIII, 378 Seiten

E-Book

PDF mit Wasserzeichen-DRM

Systemvoraussetzungen

978-3-319-65813-1 (ISBN)

53,49 €inkl. 7% MwSt.

Systemvoraussetzungen

für PDF mit Wasserzeichen-DRM

E-Book Einzellizenz

Als Download verfügbar

Beschreibung

Weitere Details

Weitere Ausgaben

Inhalt

Intro
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
Optimized 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
Extracting 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
4.1 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
4.3 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
1 Introduction: From Microblog to Cultural Contextualization
2 Data
2.1 Microblog Collection
2.2 Linked Web Pages
2.3 Wikipedia XML Corpus for Summary Generation
3 Content Analysis
4 Microblog Search
5 Timeline Illustration
6 Results
6.1 Evaluation
6.2 Participant Approaches
7 Conclusion
References
Overview of ImageCLEF 2017: Information Extraction from Images
1 Introduction
2 Overview of Tasks and Participation
3 The Lifelog Task
3.1 Motivation and Task Setup
3.2 Data Sets Used
3.3 Participating Groups and Runs Submitted
3.4 Results
3.5 Lessons Learned and Next Steps
4 The Caption Task
4.1 Task Setup
4.2 Dataset
4.3 Participating Groups and Submitted Runs
4.4 Results
4.5 Lessons Learned and Next Steps
5 The Tuberculosis Task
5.1 Task Setup
5.2 Dataset
5.3 Participating Groups and Submitted Runs
5.4 Results
5.5 Lessons Learned and Next Steps
6 The Remote (Population Estimation) Task
6.1 Motivation and Task Setup
6.2 Data Sets Used
6.3 Participating Groups and Runs Submitted
6.4 Results
6.5 Lessons Learned and Next Steps
7 Conclusions
References
Overview of the CLEF 2017 Personalised Information Retrieval Pilot Lab (PIR-CLEF 2017)
1 Introduction
2 Related Work
3 Overview of the Task
3.1 Dataset
4 Performance Measures
5 Conclusions and Future Work
References
eRISK 2017: CLEF Lab on Early Risk Prediction on the Internet: Experimental Foundations
1 Introduction
2 Pilot Task: Early Detection of Depression
2.1 Error Measure
2.2 Results
3 Future Work and Conclusions
References
CLEF 2017 Dynamic Search Evaluation Lab Overview
1 Introduction
2 Lab Overview
3 Pilot Task
3.1 Task Description and Data Sets
3.2 Participants
3.3 Evaluation
References
CLEF 2017: Multimodal Spatial Role Labeling (mSpRL) Task Overview
1 Introduction
2 Task Description
3 Annotated Corpora
4 System Descriptions
5 Evaluation Metrics and Results
6 Conclusion
References
Author Index

Systemvoraussetzungen

Als PDF speichern Als Link merken