Advances in Information Retrieval

Name: Advances in Information Retrieval | 44th European Conference on IR Research, ECIR 2022, Stavanger, Norway, April 10-14, 2022, Proceedings, Part II
Brand: Springer
Price: 106.99 EUR
Availability: OnlineOnly

44th European Conference on IR Research, ECIR 2022, Stavanger, Norway, April 10-14, 2022, Proceedings, Part II

Matthias Hagen Suzan Verberne Craig MacDonald Christin Seifert Krisztian Balog Kjetil Nørvåg Vinay Setty(Herausgeber*in)

Springer (Verlag)

Erschienen am 5. April 2022

XXX, 605 Seiten

E-Book

PDF mit Wasserzeichen-DRM

Systemvoraussetzungen

978-3-030-99739-7 (ISBN)

106,99 €inkl. 7% MwSt.

Systemvoraussetzungen

für PDF mit Wasserzeichen-DRM

E-Book Einzellizenz

Als Download verfügbar

Beschreibung

Weitere Details

Weitere Ausgaben

Inhalt

Intro
Preface
Organization
Contents - Part II
Contents - Part I
Short Papers
Improving BERT-based Query-by-Document Retrieval with Multi-task Optimization
1 Introduction
2 Preliminaries
3 Multi-task Fine-Tuning of the BERT Re-ranker
4 Experimental Setup
5 Results and Analysis
6 Conclusion
References
Passage Retrieval on Structured Documents Using Graph Attention Networks
1 Introduction
2 Proposal: Merged and Late Interaction Models
2.1 Document Graph Representation
2.2 Models Architecture
3 Experiments
3.1 Experimental Setup
3.2 Results
4 Conclusion
References
Expert Finding in Legal Community Question Answering
1 Introduction
2 Related Work
3 Data Collection and Preparation
4 Methods
4.1 Baseline 1: Probabilistic Language Modelling
4.2 Baseline 2: Vanilla BERT
4.3 Proposed Method
5 Experiments and Results
6 Conclusions
References
Towards Building Economic Models of Conversational Search
1 Introduction
2 Background
3 Models
3.1 An Economic Model of Conversational Search - Feedback First
3.2 An Economic Model of Conversational Search - Feedback After
4 Discussion and Future Work
References
Evaluating the Use of Synthetic Queries for Pre-training a Semantic Query Tagger
1 Introduction
2 Related Work
3 Experimental Setup
3.1 Dataset and Structured Corpus
3.2 Training Setup
3.3 Evaluation Metrics
4 Results and Discussion
4.1 Experiment I
4.2 Experiment II
5 Conclusion and Future Works
References
A Light-Weight Strategy for Restraining Gender Biases in Neural Rankers
1 Introduction
2 Problem Definition
3 Proposed Approach
4 Experiments
5 Concluding Remarks
References
Recommender Systems: When Memory Matters
1 Introduction
2 A Memory Aware Sequential Learning Strategy for RS
2.1 Framework
2.2 Learning Scheme
3 Experiments and Results
3.1 Datasets
3.2 Evaluation
4 Conclusion
References
Groupwise Query Performance Prediction with BERT
1 Introduction
2 Related Work
3 Method
4 Experiment Setup
5 Results
6 Conclusion
References
How Can Graph Neural Networks Help Document Retrieval: A Case Study on CORD19 with Concept Map Generation
1 Introduction
2 GNNs for Document Retrieval
2.1 Overview
2.2 Concept Maps and Their Generation
2.3 GNN-based Concept Map Representation Learning
3 Experiments
3.1 Experimental Setup
3.2 Evaluation of Concept Maps
3.3 Retrieval Performance Results
3.4 Stability and Efficiency
4 Conclusion
References
Leveraging Content-Style Item Representation for Visual Recommendation
1 Introduction and Related Work
2 Method
3 Experiments
3.1 Results
4 Conclusion and Future Work
References
Does Structure Matter? Leveraging Data-to-Text Generation for Answering Complex Information Needs
1 Introduction
2 A Data-to-text Approach for Answer Generation
3 Evaluation Setup
4 Results
5 Conclusion
References
Temporal Event Reasoning Using Multi-source Auxiliary Learning Objectives
1 Introduction
2 Related Work
3 Method
4 Experiments
4.1 Experimental Setup
4.2 Results and Analysis
5 Conclusion
References
Enhanced Sentence Meta-Embeddings for Textual Understanding
1 Introduction and Background
1.1 Preliminary Concepts
2 CINCE Framework
3 Experimental Setup
3.1 Empirical Results
4 Conclusion
References
Match Your Words! A Study of Lexical Matching in Neural Information Retrieval
1 Introduction
2 Methodology
3 Experiments
3.1 Lexical Match in Neural IR
3.2 Lexical Match and Zero-Shot Transfer Learning
4 Conclusion
References
CARES: CAuse Recognition for Emotion in Suicide Notes
1 Introduction
2 Background
3 Corpus Development
4 Cause Recognition for Emotion in Suicide Notes
4.1 Emotion Cause Identification
4.2 Emotion Cause Extraction
5 Experimental Setting
6 Results and Discussion
7 Conclusion and Future Work
References
Identifying Suitable Tasks for Inductive Transfer Through the Analysis of Feature Attributions
1 Introduction
2 Improving Performance Through Inductive Transfer
3 Optimising Transfer Learning with Explainability
4 Conclusions and Future Work
References
Establishing Strong Baselines For TripClick Health Retrieval
1 Introduction
2 Background
2.1 TripClick Collection
2.2 Re-ranking and Retrieval Models
2.3 Pre-trained BERT Instances
2.4 Related Studies
3 Experiment Design
3.1 Training Data Generation
4 TripClick Effectiveness Results
4.1 Re-ranking
4.2 Dense Retrieval
5 Conclusion
References
Less is Less: When are Snippets Insufficient for Human vs Machine Relevance Estimation?-5pt
1 Introduction
2 Related Work
3 Experiment Design
4 Results and Discussions
5 Conclusions
References
Leveraging Transformer Self Attention Encoder for Crisis Event Detection in Short Texts
1 Introduction
2 Methodology
2.1 Proposed Neural Network Architectures
3 Dataset and Experimental Setup
4 Experimental Results
5 Conclusions and Future Work
References
What Drives Readership? An Online Study on User Interface Types and Popularity Bias Mitigation in News Article Recommendations
1 Introduction
2 Experimental Setup
3 Results
3.1 RQ1: User Interface Type
3.2 RQ2: Mitigating Popularity Bias
4 Conclusion
References
GameOfThronesQA: Answer-Aware Question-Answer Pairs for TV Series
1 Introduction
2 Answer-Aware Question-Answer Pairs
2.1 Answer Span Selection
2.2 Answer Aware Question Generation (AAQG)
2.3 Question Answer Pair Output
3 Empirical Study
3.1 Settings
3.2 Evaluation Metrics
3.3 TriviaQA vs. GameofThronesQA
3.4 TweetQA vs. GameofThronesQA
3.5 WikiQA vs. GameOfThronesQA
3.6 SQuAD vs. GameOfThronesQA
4 Limitation and Conclusions
5 Appendix
References
Leveraging Customer Reviews for E-commerce Query Generation
1 Introduction
2 Related Work
3 Method
3.1 Statistics-Based Approach
3.2 Zero-Shot Generation Based on Adapted External Corpus
3.3 Ensemble Approach to Query Generation
4 Experiments
4.1 Intrinsic Similarity Evaluation
4.2 Extrinsic Retrieval Evaluation
5 Conclusion
References
Question Rewriting? Assessing Its Importance for Conversational Question Answering
1 Introduction
2 Conversational Question Answering
3 Evaluation
3.1 Experimental Setup
3.2 Results
4 Conclusions and Future Work
References
How Different are Pre-trained Transformers for Text Ranking?
1 Introduction
2 Related Work
3 Experimental Setup
4 Experiments
4.1 RQ1: How do CE and BM25 Rankings Vary?
4.2 RQ1.2: Does CE Better Rank the Same Documents Retrieved by BM25?
4.3 RQ1.3: Does CE Better Find Documents Missed by BM25?
4.4 RQ2: Does CE Incorporate ``Exact Matching''?
4.5 RQ3: Can CE Still Find ``Impossible'' Relevant Results?
5 Conclusions and Discussion
References
Comparing Intrinsic and Extrinsic Evaluation of Sensitivity Classification
1 Introduction
2 Related Work
3 Test Collections
4 Intrinsic Evaluation
5 Extrinsic Evaluation
6 Conclusions and Future Work
References
Zero-Shot Recommendation as Language Modeling
1 Introduction
2 Related Work
3 Experiments
3.1 Setup
3.2 Mining Prompts for Recommendation
3.3 Effect of the Number of Ratings Per Test User
3.4 Comparison with Matrix Factorization and NSP
3.5 Qualitative Analysis of Generations
4 Conclusion
References
What Matters for Shoppers: Investigating Key Attributes for Online Product Comparison
1 Introduction and Background
2 ReBARC: Review-Based Attribute Ranking for Product Comparison
3 Experiments and Results
4 Conclusions
References
Evaluating Simulated User Interaction and Search Behaviour
1 Introduction
2 Evaluation Methods
2.1 Kolmogorov-Smirnov-Based Evaluation
2.2 Classification-Based Evaluation
3 DataSet
4 Results
5 Conclusion
References
Multilingual Topic Labelling of News Topics Using Ontological Mapping
1 Introduction
2 Related Work
3 Experimental Setup
3.1 Models
3.2 Datasets
4 Results and Discussion
5 Conclusion
References
Demonstration Papers
ranx: A Blazing-Fast Python Library for Ranking Evaluation and Comparison
1 Introduction
2 System Overview
2.1 Qrels and Run Classes
2.2 Metrics
2.3 Comparison and Statistical Testing
2.4 The Report Class
3 Conclusion and Future Works
References
DuoSearch: A Novel Search Engine for Bulgarian Historical Documents
1 Introduction and Related Work
2 System Design
3 Evaluation
4 Conclusion and Contributions
References
Tweet2Story: A Web App to Extract Narratives from Twitter
1 Introduction
2 Tweet2Story Framework
3 Demonstration
4 Summary and Future Work
References
Patapasco: A Python Framework for Cross-Language Information Retrieval Experiments
1 Introduction
2 System Overview
2.1 Text Preprocessing
2.2 Retrieval
2.3 Reranking
2.4 Parallel Processing
3 Evaluation
4 Conclusion
References
City of Disguise: A Query Obfuscation Game on the ClueWeb
1 Introduction
2 Search System and Game Design
3 Evaluation
4 Conclusion and Future Work
References
DocTAG: A Customizable Annotation Tool for Ground Truth Creation
1 Motivation and Background
2 DocTAG
3 Final Remarks
References
ALWars: Combat-Based Evaluation of Active Learning Strategies
1 Introduction
2 Active Learning 101
3 Battle Mode
4 Demo Walkthrough
5 Conclusion
References
INForex: Interactive News Digest for Forex Investors
1 Introduction
2 System Description
2.1 Data Collection
2.2 Event Detection Algorithms
2.3 Attention Model
2.4 Interfaces and Features
3 Conclusion and Future Work
References
Streamlining Evaluation with ir-measures
1 Introduction
2 Background
3 ir-measures
4 Adoption of ir-measures
5 Conclusion
References
Turning News Texts into Business Sentiment
1 Introduction
2 S-APIR Demo System
2.1 Business Sentiment Analysis
2.2 Implementation
2.3 System Walkthrough
References
SolutionTailor: Scientific Paper Recommendation Based on Fine-Grained Abstract Analysis
1 Introduction
2 SolutionTailor Framework
2.1 Dataset Construction
2.2 Sentence Labeling and Score Calculation
2.3 Recommendation Interface
3 Evaluation
4 Conclusion
References
Leaf: Multiple-Choice Question Generation
1 Introduction
2 Related Work
3 System
4 Conclusion and Future Work
References
CLEF 2022 Lab Descriptions
Overview of PAN 2022: Authorship Verification, Profiling Irony and Stereotype Spreaders, Style Change Detection, and Trigger Detection
1 Introduction
2 Authorship Verification
3 Author Profiling
4 Multi-author Writing Style Analysis
5 Trigger Detection
References
Overview of Touché 2022: Argument Retrieval
1 Introduction
2 Task Definition
2.1 Task Description
2.2 Search Topics
3 Touché at CLEF 2021: Results and Findings
4 Conclusion
References
Introducing the HIPE 2022 Shared Task: Named Entity Recognition and Linking in Multilingual Historical Documents
1 Introduction
2 Motivation and Objectives
2.1 Significance of the Evaluation Lab
3 Overview of the Evaluation Lab
3.1 Task Description
3.2 Data Sets
3.3 Evaluation
4 Conclusion
References
CLEF Workshop JOKER: Automatic Wordplay and Humour Translation
1 Introduction
2 Background
3 Task Setup
4 Conclusion
References
Automatic Simplification of Scientific Texts: SimpleText Lab at CLEF-2022
1 Introduction
2 Background
2.1 Content Selection
2.2 Complexity Spotting
2.3 Text Simplification
3 Data Set
4 Tasks
5 Conclusion and Future Work
References
LeQua@CLEF2022: Learning to Quantify
1 Learning to Quantify
2 The Rationale for LeQua 2022
3 Structure of the Lab
3.1 Tasks
3.2 Evaluation Measures and Protocols
3.3 Data
3.4 Baselines
4 The LeQua Session at CLEF 2022
References
ImageCLEF 2022: Multimedia Retrieval in Medical, Nature, Fusion, and Internet Applications
1 Introduction
2 ImageCLEFmedical
3 ImageCLEFcoral
4 ImageCLEFaware
5 ImageCLEFfusion
6 Conclusion
References
LifeCLEF 2022 Teaser: An Evaluation of Machine-Learning Based Species Identification and Species Distribution Prediction
1 LifeCLEF Lab Overview
2 PlantCLEF Challenge: Identify the World's Flora
3 BirdCLEF Challenge: Bird Species Identification in Soundscape Recordings
4 GeoLifeCLEF Challenge: Species Prediction Based on Occurrence Data, Environmental Data and Remote Sensing Data
5 SnakeCLEF Challenge: Automated Snake Species Identification with Country-Level Focus
6 FungiCLEF Challenge: Fungi Recognition from Images and Metadata
7 Timeline and Registration Instructions
8 Conclusions and Perspectives
References
The ChEMU 2022 Evaluation Campaign: Information Extraction in Chemical Patents
1 Overview
1.1 Why Is This Campaign Needed?
1.2 How Would the Community Benefit from the Campaign?
1.3 Usage Scenarios
2 Tasks
2.1 Task 1 Expression-Level Information Extraction
2.2 Task 2 Document-Level Information Extraction
2.3 Changes Proposed for Rerunning Previous Tasks
2.4 Data and Evaluation
3 Conclusion
References
Advancing Math-Aware Search: The ARQMath-3 Lab at CLEF 2022
1 Introduction
2 ARQMath Tasks
2.1 Task 1: Answer Retrieval
2.2 Task 2: Formula Retrieval
2.3 Task 3 (Pilot): Open Domain QA for Math
3 The ARQMath Test Collection
4 Conclusion
References
The CLEF-2022 CheckThat! Lab on Fighting the COVID-19 Infodemic and Fake News Detection
1 Introduction
2 Description of the Tasks
2.1 Task 1: Identifying Relevant Claims in Tweets
2.2 Task 2: Detecting Previously Fact-Checked Claims
2.3 Task 3: Fake News Detection
3 Data
4 Evaluation Measures
5 Previously in the CheckThat! Lab
5.1 CheckThat! 2021
5.2 CheckThat! 2020
5.3 CheckThat! 2019
5.4 CheckThat! 2018
6 Related Work
7 Conclusion
References
BioASQ at CLEF2022: The Tenth Edition of the Large-scale Biomedical Semantic Indexing and Question Answering Challenge
1 Introduction
2 BioASQ Evaluation Lab 2022
2.1 Task 10a: Large-scale Biomedical Semantic Indexing
2.2 Task DisTEMIST: Disease Text Mining and Indexing Shared Task
2.3 Task 10b: Biomedical Question Answering
2.4 BioASQ Synergy 10: Question Answering for Developing Issues
2.5 BioASQ Datasets and Tools
3 The Impact of BioASQ Results
References
eRisk 2022: Pathological Gambling, Depression, and Eating Disorder Challenges
1 Introduction
2 Five Years of eRisk
2.1 Early Risk Prediction Tasks
2.2 Severity Level Estimation Task
2.3 Results
3 eRisk 2022
4 Conclusions
References
Doctoral Consortium
Continually Adaptive Neural Retrieval Across the Legal, Patent and Health Domain
1 Motivation
2 Research Questions
3 Background and Related Work
4 Methods and Experiments
4.1 RQ-1.3: How Well Do Approaches for Neural Retrieval in the First Stage Retrieval Generalize Across Different Domains?
4.2 RQ-2: How Can We Continually Adapt Neural Retrieval Models for In-Production Systems?
5 Research Issues
References
Understanding and Learning from User Behavior for Recommendation in Multi-channel Retail
1 Motivation
2 Related Work
3 Proposed Research and Methodology
3.1 Understanding Customer Behavior
3.2 Recommendation in Multi-channel Retail
4 Research Issues for Discussion
References
An Entity-Oriented Approach for Answering Topical Information Needs
1 Introduction
2 Related Work
3 Methodology
4 Conclusion
References
Cognitive Information Retrieval
1 Introduction and Thesis Objectives
2 Research Methodology
2.1 RQ1: How to Extract and Represent the User's Knowledge?
2.2 RQ2: How to Model the User's Search Goals?
2.3 RQ3: How to Design the Framework Architecture
2.4 RQ3: How to Employ the Cognitive Aspects to Personalise Results?
2.5 RQ4: How to Evaluate the Model?
3 Conclusion
References
Graph-Enhanced Document Representation for Court Case Retrieval
1 Introduction and Motivation
2 Related Work
3 Research Description and Research Questions
4 Methodology
References
Relevance Models Based on the Knowledge Gap
1 Motivation and Problem Statement
2 Research Questions
3 Background and Related Work
3.1 Knowledge Gap
3.2 Knowledge Delta
4 Research Methodology
References
Evidence-Based Early Rumor Verification in Social Media
1 Introduction
2 Related Work
3 Proposed Methodology
3.1 RQ1: Authority Finding
3.2 RQ2: Evidence Retrieval from Twitter
3.3 RQ3: Effective Explainable Early Rumor Verification
4 Experimental Evaluation
5 Issues for Discussion
References
Multimodal Retrieval in E-Commerce*2mm
1 Motivation
2 Related Work
3 Research Description and Methodology
References
Medical Entity Linking in Laypersons' Language
1 Motivation
2 Background and Related Work
3 Proposed Research
4 Research Methodology and Proposed Experiments
4.1 Data Sets Available
4.2 Data Augmentation and Distant Supervision
4.3 Informal Medical Entity Linking
4.4 Evaluation
References
A Topical Approach to Capturing Customer Insight Dynamics in Social Media
1 Introduction
2 Background and Research Questions
3 Research Methodology
4 Related Works
5 Research Progress and Future Works
6 Specific Research Issues for Discussion at the Doctoral Consortium
References
Towards Explainable Search in Legal Text
1 Motivation
2 Related Work
3 Approach and Preliminary Results
4 Proposed Research Questions and Methodology
5 Research Issues for Discussion
References
End to End Neural Retrieval for Patent Prior Art Search
1 Introduction
2 Patent Search Characteristics
3 Research Questions
4 Summary of My Research so Far
References
Workshops
Third International Workshop on Algorithmic Bias in Search and Recommendation (BIAS@ECIR2022)
1 Introduction
2 Workshop Vision and Topics
3 Workshop Organizers
References
The 5thInternational Workshop on Narrative Extraction from Texts: Text2Story 2022
1 Motivation
2 Scientific Objectives
3 Organizing Team
References
Augmented Intelligence in Technology-Assisted Review Systems (ALTARS 2022): Evaluation Metrics and Protocols for eDiscovery and Systematic Review Systems
1 Motivations
2 Topics of Interest
3 Organizing Team
References
Bibliometric-enhanced Information Retrieval: 12th International BIR Workshop (BIR 2022)
1 Motivation and Relevance to ECIR
2 Workshop Goals/Objectives
3 Target Audience and Dissemination
4 Peer Review Process and Workshop Format
5 Organisers and Programme Commitee
References
ROMCIR 2022: Overview of the 2nd Workshop on Reducing Online Misinformation Through Credible Information Retrieval
1 Introduction
2 Topics of Interest
3 Previous Edition
4 Organizers
4.1 Workshop Chairs
4.2 Proceedings Chair
4.3 Program Committee
References
Tutorials
Online Advertising Incrementality Testing: Practical Lessons, Paid Search and Emerging Challenges-5pt
1 Learning Objectives and Scope
2 Tutorial Outline
3 Authors Biography
4 List of References by Topic
4.1 The need for Incrementality Testing Solutions
4.2 Incrementality Testing Solutions
4.3 Causal Inference
4.4 Operationalization and Practical Recommendations
4.5 Paid Search Incrementality Testing
4.6 Geo-testing and Synthetic Control and Identity Challenges
References
From Fundamentals to Recent Advances: A Tutorial on Keyphrasification
1 Presenters
2 Why is This Tutorial Important?
3 Target Audience and Prerequisite Knowledge
4 Format of the Tutorial
5 Participation Encouragement
References
Information Extraction from Social Media: A Hands-On Tutorial on Tasks, Data, and Open Source Tools
1 Introduction
1.1 Aims and Learning Objectives
1.2 Scope and Benefit to the ECIR Community
1.3 Presenter Bios
2 Tutorial Details
References
ECIR 2022 Tutorial: Technology-Assisted Review for High Recall Retrieval
1 Introduction
2 Full Description
3 Presenters and Their Credentials
References
Author Index

Systemvoraussetzungen

Als PDF speichern Als Link merken