Presentation Instructions

Full papers and Best Of the Labs papers presentation

Each paper is allocated 30 minutes for lecture, including time for questions and session-chair introduction.

Full papers with short presentation

For each paper, a short presentation (10 minutes with no discussion afterwards) as well as a poster are needed. Discussion on papers will take place during the poster session directly following the session.

For your poster, a board will be provided; the board is oriented in a “portrait” format and poster should be in A0 format (84,1cm wide and 118cm tall - approximately 33in wide and 46.5in tall).

Short papers presentation : posters

For your poster, a board will be provided; the board is oriented in a “portrait” format and poster should be in A0 format (84,1cm wide and 118cm tall - approximately 33in wide and 46.5in tall).

Labs posters

For your poster, a board will be provided; the board is oriented in a “portrait” format and poster should be in A0 format (84,1cm wide and 118cm tall - approximately 33in wide and 46.5in tall).

CLEF 2015 Accepted Papers

Best of the labs papers

• Search-based Image Annotation: Extracting Semantics from Similar Images (long presentation)
  Petra Budikova, Michal Batko, Jan Botorek and Pavel Zezula.
• NLP-based classifiers to generalize experts assessments in E-Reputation monitoring (long presentation)
  Jean-Valère Cossu, Emmanuel Ferreira, Killian Janod, Julien Gaillard and Marc El-Bèze.
• A Method for Short Message Contextualization: Experiments at CLEF/INEX (long presentation)
  Liana Ermakova.
• Towards Automatic Large-Scale Identification of Birds in Audio Recordings (long presentation)
  Mario Lasseck.
• Information Extraction From Clinical Documents: Towards Disease/Disorder Template Filling (short presentation)
  Veera Raghavendra Chikka, Nestor Mariyasagayam, Yoshiki Niwa and Kamalakar Karlapalem.
• Adaptive Algorithm for Plagiarism Detection(long presentation)
  Miguel A. Sánchez-Pérez, Alexander Gelbukh and Grigori Sidorov.
• Optimizing and Evaluating Stream-based News Recommendation Algorithms (long presentation)
  Sebastian Werner and Andreas Lommatzsch.
• Answering Natural Language Questions via Phrasal Semantic Parsing (long presentation)
  Kun Xu, Yansong Feng and Dongyan Zhao.

Full papers (long presentation)

• Experimental Study on Semi-Structured Peer-to-Peer Information Retrieval Network
  Rami Alkhawaldeh and Joemon Jose.
• Evaluating Stacked Marginalised Denoising Autoencoders within Domain Adaptation Methods
  Boris Chidlovskii, Gabriela Csurka and Stephane Clincahnt.
• Language Variety Identification using Distributed Representations of Words and Documents
  Marc Franco-Salvador, Francisco Rangel, Paolo Rosso, Mariona Taulé and M. Antònia Martí.
• Evaluating User Image Tagging Credibility
  Alexandru Lucian Gînscă, Adrian Popescu, Mihai Lupu, Adrian Iftene and Ioannis Kanellos.
• Tweet Expansion Method for Filtering Task in Twitter
  Payam Karisani, Farhad Oroumchian and Maseud Rahgozar.
• Real-Time Entity-Based Event Detection for Twitter
  Andrew J Mcminn and Joemon Jose.
• A Comparative Study of Click Models for Web Search
  Luka Stout, Finde Xumara, Ilya Markov, Artem Grotov, Aleksandr Chuklin and Maarten de Rijke.
• Evaluation of Pseudo Relevance Feedback Techniques for Cross Vertical Aggregated Search
  Hermann Ziak and Roman Kern.

Full papers (short presentation)

• Analysing the Role of Representation Choices in Portuguese Relation Extraction
  Sandra Collovini, Marcelo de Bairros Pereira Filho and Renata Vieira.
• An Investigation of Cross-Language Information Retrieval for User-Generated Internet Video
  Ahmad Khwileh, Debasis Ganguly and Gareth Jones.
• Benchmark of Rule-based Classifiers in the News Recommendation Task
  Jaroslav Kuchař and Tomas Kliegr.
• Enhancing Medical Information Retrieval by exploiting a Content-Based Recommender Method
  Wei Li and Gareth Jones.
• Summarizing Citation Contexts of Scientific Publications
  Sandra Mitrović and Henning Müller.
• A Multiple-stage Approach to Re-ranking Medical Documents
  Heung-Seon Oh, Yuchul Jung and Kwang-Young Kim.
• Exploring Behavioral Dimensions in Session Effectiveness through Simulation
  Teemu Pääkkönen, Heikki Keskustalo, Jaana Kekäläinen, Leif Azzopardi, David Maxwell, Feza Baskaya and Kalervo Järvelin.

Short papers

• Meta Text Aligner: Text Alignment Based on Predicted Plagiarism Relation
  Samira Abnar, Mostafa Dehghani and Azadeh Shakery.
• Automatic Indexing of Journal Abstracts with Latent Semantic Analysis
  Joel Adams and Steven Bedrick.
• Shadow Answers as an Intermediary in Email Answer Retrieval
  Alyaa Alfalahi, Gunnar Eriksson and Eriks Sneiders.
• Are Topically Diverse Documents Also Interesting?
  Hosein Azarbonyad, Ferron Saan, Mostafa Dehghani, Maarten Marx and Jaap Kamps.
• Modeling of the Question Answering Task in the YodaQA System
  Petr Baudis and Jan Sedivy.
• Unfair Means: Use Cases beyond Plagiarism
  Paul Clough, Peter Willett and Jesse Lim.
• INSTANCE-BASED LEARNING FOR TWEET MONITORING AND CATEGORIZATION
  Julien Gobeill, Arnaud Gaudinat and Patrick Ruch.
• Are Test Collections ”Real”? - Mirroring Real-World Complexity in IR Test Collections
  Melanie Imhof and Martin Braschler.
• Evaluation of Manual Query Expansion Rules on a Domain Specific FAQ Collection
  Mladen Karan and Jan Snajder.
• Evaluating Learning Language Representations
  Jussi Karlgren, Jimmy Callin, Kevyn Collins-Thompson, Amaru Cuba Gyllensten, Ariel Ekgren, David Jürgens, Anna Korhonen, Fredrik Olsson, Magnus Sahlgren and Hinrich Schütze.
• Automatic Segmentation and Deep Learning of Bird Sounds
  Hendrik Vincent Koops, Jan van Balen and Frans Wiering.
• The Impact of Noise in Web Genre Identification
  Dimitrios Pritsos and Efstathios Stamatatos.
• On the Multilingual and Genre Robustness of EmoGraphs for Author Profiling in Social Media
  Francisco Manuel Rangel Pardo and Paolo Rosso.
• Is Concept Mapping useful for Biomedical Information Retrieval?
  Wei Shen and Jian-Yun Nie.
• Using Health Statistics to Improve Medical and Health Search
  Tawan Sierek and Allan Hanbury.
• Determining Window Size from Plagiarism Corpus for Stylometric Features
  Šimon Suchomel and Michal Brandejs.
• Effect of log-based Query Term Expansion on Retrieval Effectiveness in Patent Searching
  Wolfgang Tannebaum, Andreas Rauber and Parvaz Mahdabi.
• Integrating Mixed-Methods for Evaluating Information Access Systems
  Simon Wakeling and Paul Clough.
• Teaching the IR process using real experiments supported by game mechanics
  Thomas Wilhelm-Stein and Maximilian Eibl.
• Tweet Contextualization Using Association Rules Mining and DBpedia
  Meriem Amina Zingla, Chiraz Latiri and Yahya Slimani.