Conference Sessions


Session 1 (Day 1): NLU and Document Analysis

  • 10:00-10:20 SimpleText Best of Labs in CLEF-2023: Scientific Text Simplification Using Multi-Prompt Minimum Bayes Risk Decoding - Andrianos Michail, Pascal Severin Andermatt and Tobias Fankhauser
  • 10:20-10:40 Assessing Document Sanitization for Controlled Information Release and Retrieval in Data Marketplaces - Luca Cassani, Giovanni Livraga and Marco Viviani

Session 2 (Day 2): Social Media, Multilinguality and Decision-Making

  • 14:00-14:20 Who Will Evaluate the Evaluators? Exploring the Gen-IR User Simulation Space (position paper) - Johannes Kiesel, Marcel Gohsen, Nailia Mirzakhmedova, Matthias Hagen and Benno Stein
  • 14:20-14:40 Leveraging LLM-Generated Data for Detecting Depression Symptoms on Social Media - Ana-Maria Bucur
  • 14:40-15:00 Large Language Model Cascades and Persona-based In-context Learning for Multilingual Sexism Detection - Lin Tian, Nannan Huang and Xiuzhen Zhang
  • 15:00-15:20 Mapping the Media Landscape: Predicting Factual Reporting and Political Bias Through Web Interactions - Dairazalia Sanchez-Cortes, Sergio Burdisso, Esau Villatoro-Tello and Petr Motlicek
  • 15:20-15:40 Best of Touché 2023 task 4: Testing Data Augmentation and Label Propagation for Multilingual multi-target Stance Detection - Jorge Avila, Alvaro Rodrigo and Roberto Centeno

Session 3 (Day 3): Datasets

  • 10:00-10:20 KAPR: A dataset for Evaluation of Ranking Models for a Knowledge Acquisition Passage Retrieval Task - Artemis Capari, Hosein Azarbonyad, Georgios Tsatsaronis, Jaap Kamps, Zubair Afzal and Judson Dunham
  • 10:20-10:40 De-Noising Document Classification Datasets via Prompt-based Rank Pruning: A Case Study - Matti Wiegmann, Martin Potthast and Benno Stein

Session 4 (Day 4): In-Context Evaluation and Retrieval

  • 9:00-9:20 From Sentence Embeddings to Large Language Models to Detect and Understand Wordplay - Ryan Rony Dsilva
  • 9:20-9:40 Replicability Measures for Longitudinal Information Retrieval Evaluation - Jüri Keller, Timo Breuer and Philipp Schaer
  • 9:40-10:00 The Impact of Web Search Result Quality on Decision-Making - Jan Heinrich Reimer, Lena Merker and Alexander Bondarenko
  • 10:00-10:20 Improving Laypeople Familiarity with Medical Terms by Informal Medical Entity Linking - Annisa Maulida Ningtyas, Alaa El-Ebshihy, Florina Piroi and Allan Hanbury
  • 10:20-10:40 SessionPrint: Accelerating kNN via Locality-Sensitive Hashing for Session-based News Recommendation - Mozhgan Karimi

Session 5 (Day 4): Classification

  • 16:00-16:20 Under-sampling strategies for better transformer-based classifications models - Marcin Sawinski, Krzysztof Węcel and Ewelina Księżniak
  • 16:20-16:40 Classification of social media hateful screenshots inciting violence and discrimination - Davide Buscaldi, Paolo Rosso, Berta Chulvi and Ting Wang
  • 16:40-17:00 Sexism Identification on TikTok: A Multimodal AI Approach with Text, Audio, and Video - Iván Arcos and Paolo Rosso