The 2nd ACM International Conference on the Theory of Information Retrieval
University of Delaware, Newark, DE, USA
September 13-16, 2016
slideshow 1 slideshow 2 slideshow 3

You are here

ICTIR 2016 Tutorials

Four tutorials will be presented at ICTIR 2016, one full-day and three half-day. One half-day is included in the base registration fee; additional half-days can be added separately.

Tutorial 1 (full-day): Advances in Formal Models of Search and Search Behavior
Leif Azzopardi
University of Strathclyde
Guido Zuccon
Queensland University of Technology
Searching is performed in the context of a task and as such the value of the information found is with respect to the task. Recently, there has been a drive to developing formal models of information seeking and retrieval that consider the costs and benefits arising through the interaction with the interface/system and the information surfaced during that interaction. In this full day tutorial we will focus on describing and explaining some of the more recent and latest formal models of Information Seeking and Retrieval. The tutorial is structured into two parts. In the first part we will present a series of models that have been developed based on: (i) economic theory, (ii) decision theory (iii) game theory and (iv) optimal foraging theory. The second part of the day will be dedicated to building models where we will discuss different techniques to build and develop models from which we can draw testable hypotheses from. During the tutorial participants will be challenged to develop various formals models, applying the techniques learnt during the day. We will then conclude with presentations on solutions followed by a summary and overview of challenges and future directions. This tutorial is aimed at participants wanting to know more about the various formal models of information seeking, search and retrieval, that have been proposed. The tutorial will be presented at an intermediate level, and is designed to support participants who want to be able to understand and build such models.

Dr. Leif Azzopardi has been recently awarded a Chancellor's Fellowship at the University of Strathclyde within the Department of Computer and Information Sciences. Prior to this appointment, he was a Senior Lecturer in the School of Computing Science at the University of Glasgow. His research focuses on building formal models for Information Retrieval - usually drawing upon different disciplines for inspiration, such as Quantum Mechanics, Operations Research, Microeconomics, Transportation Planning and Gamification.
He received his Ph.D. in Computing Science from the University of Paisley in 2006, and he received a First Class Honours Degree in Information Science from the University of Newcastle, Australia, 2001. In 2010, he received a Post-Graduate Certificate in Academic Practice and has been lecturing at the University of Glasgow since then. He has given numerous invited talks on Formal Models of Information Seeking and Retrieval throughout the world and lectured at the Information Foraging Summer School (2011, 2012 and 2013) and Symposium of Future Directions in Information Access (2007-2013).

Dr. Guido Zuccon is a lecturer within the School of Information Systems at the Queensland University of Technology. His research interests include formal models of search, ranking principles for information retrieval, and retrieval models for health search. Guido has actively contributed to the area of document ranking and search result diversification. During his Ph.D. he performed an extensive analysis of document ranking principles and introduced the quantum probability ranking principle and was the first to empirically evaluate the interactive PRP. His work on formal models of search result diversification based on facility location analysis received the best paper award at ECIR 2013 and then in 2014 he received a best reviewer award at ECIR.
He received a Ph.D. in Computing Science from the University of Glasgow in 2012, and he received a Master in Computer Engineering with summa cum laude from the University of Padua, Italy, in 2007. Before joining the Queensland University of Technology as a lecturer in 2014, he was a postdoctoral research fellow at the CSIRO, Australia.

Tutorial 2 (half-day): Utilizing Knowledge Bases in Text-centric Information Retrieval
Laura Dietz
University of New Hampshire, USA
Alexander Kotov
Wayne State University, USA
Edgar Meij
Bloomberg L.P., UK
General-purpose knowledge bases are increasingly growing in terms of depth (content) and width (coverage). Moreover, algorithms for entity linking and entity retrieval have improved tremendously in the past years. These developments give rise to a new line of research that exploits and combines these developments for the purposes of text-centric information retrieval applications.

This tutorial focuses on a) how to retrieve a set of entities for an ad-hoc query, or more broadly, assessing relevance of KB elements for the information need, b) how to annotate text with such elements, and c) how to use this information to assess the relevance of text. We discuss different kinds of information available in a knowledge graph and how to leverage each most effectively.

Prof. Dr. Laura Dietz is a professor at University of New Hampshire, where she teaches Information Retrieval and Machine Learning. Before that she was working in the Data and Web Science group at Mannheim University, with Prof. Bruce Croft and Prof. Andrew McCallum at University of Massachusetts, and obtained her Ph.D. from the Max Planck Institute for Informatics. Her research focuses on text processing and information retrieval with knowledge bases. Her scientific contributions span from entity linking to the prediction of influences in citation graphs. In this tutorial, she will cover her seminal publication on entity query feature expansion and her work on finding relevant relations.

Prof. Dr. Alexander Kotov is an Assistant Professor in the Department of Computer Science at Wayne State University. His general research interests lie at the intersection of information retrieval, textual data mining and health informatics. Before joining Wayne State, he was a post-doctoral fellow at Emory University working with Prof. Eugene Agichtein. Dr. Kotov obtained his PhD from the University of Illinois at Urbana-Champaign, under the supervision of Professor ChengXiang Zhai. At Wayne State has been teaching graduate courses on Information Retrieval and NoSQL databases as well as undergraduate courses. This tutorial will cover his work on using semantic networks for query expansion and his recent work on entity retrieval from knowledge graphs.

Dr. Edgar Meij is a senior scientist at Bloomberg. Before this, he was a research scientist at Yahoo Labs and a postdoc at the University of Amsterdam, where he also obtained his Ph.D. He regularly teaches at the (post-)graduate level, including university courses and conference tutorials, e.g., at EACL 2009, SIGIR 2013, WWW 2013, and WSDM 2014. His research focuses on all applications and aspects of knowledge graphs, entity linking, and semantic search. This tutorial will cover his contributions on entity aspect mining and finding support passages for relations.

Tutorial 3 (half-day): Collaborative Information Retrieval: frameworks, theoretical models and emerging topics
Lynda Tamine
University of Toulouse UPS - IRIT, France
Laure Soulier
Sorbonne Universites, UPMC Univ Paris 06 - LIP6
A great amount of research in the IR domain mostly dealt with both the design of enhanced document ranking models allowing search improvement through user-to-system collaboration. The latter is perceived as part of the search process leading to an interactive process where the system learns from the user and adapts the search accordingly. However, in addition to user-to-system form of collaboration, user-to-user collaboration is increasingly acknowledged as an effective means for gathering the complementary skills and/or knowledge of individual users in order to solve complex search tasks, such as fact-finding tasks (e.g., travel planning) or exploratory search tasks [23, 31]. Collaboration allows the group achieving a result that is more effective than the simple aggregation of the individual results [25]. This tutorial will first give an overview of the ways into collaboration has been implemented in IR models with the attempt of improving the search outcomes with respect to several tasks and related frameworks (ad-hoc search, group-based recommendations, social search, collaborative search). Second, as envisioned in collaborative IR domain (CIR), we will focus on the theoretical models that support and drive user-to-user collaboration in order to perform shared IR tasks. Third, we will develop a road map on emerging and relevant topics addressing issues related to collaboration design. Our goal is to provide participants with concepts and motivation to allow them to investigate this emerging IR domain as well as giving them some clues on how to tackle issues related to the optimization of collaborative tasks. The participants will also have an opportunity to share their experience within orthogonal research domains.
More specifically, the tutorial aims to:
1. Give an overview of the key concept of collaboration in IR and related research topics;
2. Present state-of-the art CIR techniques and models;
3. Discuss about the emerging topics that deal with collaboration;
4. Point out some challenges ahead.

Lynda Tamine is a full Professor at Paul Sabatier University and member of the Institut de Recherche en Informatique de Toulouse, France. Her research interests include modeling and evaluation of contextual, collaborative, social, and medical IR. Since May 2015, she is the head of the IRIT research theme on ”Information Retrieval and indexing” and was a member of the French association on IR and applications (ARIA) during the period 2007-2014. She leads and/or is involved in several IR related research projects. She co-organized several IR related scientific events including the CIRSE international workshop 2009-2010 on the evaluation of contextual IR (with Joemon Jose, Massimo Melucci and Biech Lien), french autumn school on IR EARIA 2012 (with Eric Gaussier), french workshop on social IR 2010-2012 (with Eric Gaussier and Gregory Grefenstette) and recently, on march 2016, the french conference on IR SDNRI 2016 (with Gilles Hubert and Nadine Jessel). She has a relevant record of publications within the tutorial topic including sub-topics related to the design of system-driven CIR (CIR) models (IP&M 2014, SIGIR 2014, IP&M accepted in april 2016) and user’s behaviour understanding within a CIR framework (CIKM 2015). She has co-organized, with Laure Soulier, Leif Azzopardi, Testsuya Sakai and Jeremy Pickens, the 1st workshop on the Evaluation of Collaborative Information Retrieval and Seeking (Ecol) in conjunction with the 24th Conference on Information and Knowledge Management (CIKM’2015)

Laure is an associate professor at the Pierre and Marie Curie University and joined the “Laboratoire d’Informatique de Paris 6” (LIP6) since September 2015. She is interested in Information Retrieval and more particularly in the CIR research field in which she obtained her PhD in 2014 in Paul Sabatier University (Toulouse). With Lynda Tamine, she proposed several contributions dealing with collaborative ranking models relying either on the domain expertise of users as well as their roles. Significant publications have been accepted at AIRS 2013 (Best paper Award), IP&M 2014 and 2016 (recently accepted), SIGIR 2014 and CIKM 2015. Laure has collaborated with Chirag Shah at the University of Rutgers for a 3-month internship where she worked on role analysis and detection for CIR. She co-organizes with Lynda Tamine, Leif Azzopardi, Tetsuya Sakai, and Jeremy Pickens a CIKM workshop (ECol 2015) dealing with the Evaluation of Collaborative Information Retrieval and Seeking. She also co-presented with Lynda Tamine a tutorial at ECIR 2016 on Collaborative Information Retrieval (CIR 2016).

Tutorial 4 (half-day): Topic Set Size Design and Power Analysis in Practice
Tetsuya Sakai
Waseda University
Topic set size design methods provide principles and procedures for test collection builders to decide on the number of topics to create. These methods can then help us keep improving the test collection design based on accumulated data. Simple Excel tools are available for such purposes. Post-hoc power analysis tools, available as simple R scripts, can help IR researchers examine the achieved power of a reported experiment and determine future sample sizes for ensuring high power. Thus, for example, underpowered user experiments can be detected, and a larger sample size can be proposed. If used appropriately,these Excel and R tools should be able to provide the IR community with better experimentation practices. The main objective of this tutorial is to let IR researchers familiarise themselves with these tools and understand the basic ideas behind them.

Based on the reviewers' comments I received, I will start from the basics of statistical significance testing.

Tetsuya Sakai is a professor at the Department of Computer Science and Engineering, Waseda University, Japan. He is also an Associate Dean at the IT Strategies Division of Waseda, and a visiting professor at the National Institute of Informatics. He joined Toshiba in 1993. He obtained a Ph.D from Waseda in 2000. From 2000 to 2001, he was a visiting reseacher at the Computer Laboratory, University of Cambridge, where he was supervised by the late Karen Sparck Jones. In 2007, he joined a startup as the director of the Natural Language Processing Lab. In 2009, he joined Microsoft Research Asia. He joined the Waseda faculty in 2013. He is an editor-in-chief of the Information Retrieval Journal (Springer), an associate editor of ACM TOIS. He is a general co-chair of NTCIR. He is also a general co-chair of ACM SIGIR 2017.

Theme by Danetsoft and Danang Probo Sayekti inspired by Maksimer