The 36th European Conference on IR Research (ECIR2014) was held in the beautiful city of Amsterdam on 13-16 April 2014. With its objective to provide the venue for the presentation and publication of the original research outcome in various domains of Information Retrieval, the conference provided a diverse range of opportunities, i.e., workshops, tutorials, short papers (posters/demos), full papers, Industry sessions, for the participation and dissemination of research.
The conference started with the workshops and tutorials day on 13th April. The workshops were arranged in full day and half day sessions, based on the contents and the proposals. The full day workshops were on Information Access in Smart Cities where the theme was:
“Modern cities are becoming smart where a digital knowledge infrastructure is deployed by local authorities (e.g. City councils and municipalities) to better serve the information needs of their citizens, and to ensure sustainability and efficient use of power and resources. This knowledge infrastructure consists of a wide range of systems from low-level physical sensors to advanced sensing devices through social sensors. This proposed workshop will be a venue for research on digesting the city’s data streams and knowledge databases in order to serve the information needs of citizens and support decision making for local authorities. Possible use cases include helping tourists to find interesting places to go or activities to do while visiting a city, or assisting journalists in reporting local incidents. Indeed, this workshop will foster the development of new information access and retrieval models that can harness effectively and efficiently the large number of heterogeneous big data streams in a city to provide a new generation of information services.”
and on Context Aware Retrieval and Recommendations with the theme:
“Context-aware information is widely available in various ways, such as interaction patterns, devices, annotations, query suggestions and user profiles and is becoming more important for enhancing retrieval performance. At the moment, the main issue to cope with is not only retrieving the most relevant items and content, but defining them ad hoc. Further relevant issues are personalizing and adapting the information and the way it is displayed to the users current situation (device, location, social surrounding) and interests. In the 4th edition of the workshop we want to focus on integrating social context into retrieval and recommendation.”
The half day workshops were offered on Bibliometric-Enchanced Information Retrieval with the aim:
“Bibliometric techniques are not yet widely used to enhance retrieval processes in digital libraries, although they offer value-added effects for users. In this workshop we will explore how statistical modelling of scholarship, such as Bradfordizing or network analysis of coauthorship network, can improve retrieval services for specific communities, as well as for large, cross-domain collections. This workshop aims to raise awareness of the missing link between In-formation Retrieval (IR) and bibliometrics/scientometrics and to create a common ground for the incorporation of bibliometric-enhanced services into retrieval at the digital library interface.”
and Gamification for Information Retrieval based on the theme:
“Gamification is the application of game mechanics such as leaderboards, badges or achievement points in non-gaming environments. The goal is to achieve more accurate work, better retention rates, and a more cost-effective solution by relating motivations for participating as more intrinsic than conventional methods. Gamification has recently emerged as a major research area, however its adoption in Information Retrieval (IR) is still in its infancy despite the fact that there are many IR tasks that could potentially benefit from gamification techniques including the manual annotation of documents in IR evaluation, the participation in user studies to study interactive IR challenges, and the move from single-user search to social search. This workshop intends to narrow down and focus on the challenges and opportunities that gamification can present for the IR community. We aim to bring together researchers and practitioners from a wide range of areas including information retrieval, human-computer interaction, computer games, and natural language processing.”
The large number of delegates participated in the workshops in terms of submissions, presentations and discussion. The formats and executions of the workshops were decided by the respective local chairs.
The tutorials were: “Text Quantification” by Fabrizio Sebastiani from Consiglio Nazionale delle Ricerche, Italy , Designing Search Usability by Tony Russell-Rose from UXLabs UK and the Cluster Hypothesis in Information Retrieval by Oren Kurland from Technion – Israel Institute of Technology. The tutorials covered the respective domain from basic to advanced level and provided the holistic perspective on the respective topics.
After the workshops and tutorial sessions the social welcome reception was at Riva Amsterdam, a nice venue on the canal with the capacious space and the beautiful view of the canal.
The reception lasted till late with the participants socializing and discussing about their interests and enjoying the drinks and snacks.
The second day of the conference started with the welcome note by Maarten de Rijke. In order to celebrate and appreciate the contributions and the legacy of Karen Spärck Jones, this year’s award was announced to be awarded to Eugene Agichtein, Mathematics and Computer Science Department, Emory University, Atlanta, USA. The keynote session was chaired by Ayse Goker.
Eugene’s KSJ Award Keynote speech was about “Inferring Searcher Attention and Intention by Mining Behavior Data”. The talk highlighted the advancements in user-centered IR, the current state of the art and the future directions to incorporate cognitive information to enhance the search experience. Following is the abstract of the talk:
“A long standing challenge in Web search is how to accurately determine the intention behind a searchers query, which is needed to rank, organize, and present results most effectively. The difficulty is that users often do not (or cannot) provide sufficient information about their goals. As this talk with show, it is nevertheless possible to read their intentions through clues revealed by behavior, such as the amount of attention paid to a document or a text fragment. I will overview the approaches that have emerged for acquiring and mining behavioral data for inferring search intent, ranging from robust models of click data in the aggregate, to modeling fine-grained user interactions such as mouse cursor movements in the searchers browser. The latter can also be used to measure the searchers attention “in the wild, with granularity approaching that of using eye tracking equipment in the laboratory. The resulting techniques and models have already shown noteworthy improvements for search tasks such as ranking, relevance estimation, and result summary generation, and have applications to other domains, such as psychology, neurology, and online education.”
After the coffee break the main conference started in parallel sessions. Session 1A on Evaluation was chaired by Pavel Serdyukov and Session 1B on Recommendations was chaired by Leif Azzopardi.
ECIR 2014 offered two poster and demo sessions on different days. The first poster and demo session started after lunch. In the poster sessions the short papers were presented. The first session consisted of 25 posters and 8 demos presenting various IR applications. The poster and demo sessions drew the attention of participants as the lively discussions showed. Posters and demos were numbered to keep record for the best poster and demo award. Each delegate had to vote for the best demo and best poster award.
After the coffee break the second set of parallel sessions started. The session 2A on Optimization and Prediction was chaired by Eric Gaussier and session 2B on Semantics and Annotations was chaired by Edgar Meij, with three presentations in each session.
The second day ended with the women networking event, where female participants of the conference gathered and socialized to celebrate the role of women in computer science.
At the end of the second day some downtown drinks were arranged, the participation was discretionary, still many participants enjoyed the downtown venue and drinks.
The third day of the conference on Tuesday 15th April, started with the welcome note by Maarten de Rijke, followed by the panel on the “Panel on Information Retrieval Research Ecosystem”. Mark Sanderson from RMIT University moderated the panel and the panellists were from academia and industry. Norbert Fuhr from the University of Duisburg-Essen and Birger Larsen from Aalborg University, Denmark participated as the academicians while for the industry side Pavel Serdyukov from Yandex and Peter Mika form Yahoo! Labs were on the panel. The main objective was to portray the overall landscape of information retrieval where academic and industry scale research is taking place. The panellists emphasized on the reproducibility of the experiment results with the open public datasets. The industry should consider the joint venture with the academia and facilitate the researchers to collaborate and make use of data there to enhance the overall research in IR. The panellists from industry highlighted some of the provisions and internships that help researchers in academia to collaborate and make use industry data. The panel replied the questions from audiences as well. In the end Mark concluded by highlighting some of the advancements in IR research in general.
After the coffee break the parallel sessions of the third conference day started. Session 3A Evaluation II was chaired by Jaime Arguello and the session 3B on Aggregation was chaired by Fabio Crestani.
After the lunch break the second poster and demo session took place where 25 posters and 7 demos were presented. Like the first poster and demo session this session also remained lively and interactive. The participants showed keen interest in poster presentations and the demos.
One of the highlights of ECIR 2014 was “Boat ‘n’ Banquet”, a boat trip on the Amstel river followed by the banquet at Jamie Oliver’s Fifteen Restaurant. The boat route was passing through the city center so that the participants could experience the beautiful view of the Amsterdam City from the boat. To many sightseeing from the boat was a new and exciting experience, hence the participants enjoyed the boat trip and captured the moments in cameras.
The boat left the participants near the Jamie Oliver’s Fifteen Restaurant. On the arrival drinks were served, followed by announcements for the best paper, poster and demo awards. Maarten de Rijke and John Tait announced the awards for the best paper, best poster, best demo and the best reviewer awards, the latter being a new award introduced at ECIR 2014. The best paper award went to Matteo Catena, Craig Macdonald and Iadh Ounis for their paper “On Inverted Index Compression for Search Engine Efficiency”.
The best poster award was given for “A Language Modeling Approach to Personalized Search Based on Users’ Microblog Behavior” by Arjumand Younus, Colm O’Riordan and Gabriella Pasi.
The “TripBuilder: A Tool for Recommending Sightseeing Tours” by Igo Ramalho Brilhante, Jose Antonio Macedo, Franco Maria Nardini, Raffaele Perego, Chiara Renso, was elected by the delegates for the best demo award. The best reviewer awards were given to Tao Yang, Guido Zuccon, Yannis Tzitzikas and Carsten Eickhoff, for their very informative and keen reviewing. After the award ceremony Norbert Fuhr thanked and appreciated Maarten de Rijke and the conference organization committee for their efforts on making the conference experience the best.
At the end of the awards dinner was served. The conference organizers arranged the tram tickets for the participants to the Amsterdam Central station where after everyone went to their respective accommodations or out to enjoy a further piece of Amsterdam’s nightlife.
Wednesday, 16th April was the fourth and final day of the conference, which started with the opening note by Maarten de Rijke. He thanked the generous sponsors and presented some facts about the conference so far. As the final day was designated mainly to industry, the key-note speaker was Gilad Mishne from Twitter who presented on the topic “Real-time Search at Twitter”: “Twitter’s search engine faces some of the most unique challenges in information retrieval and distributed systems today. On the scaling front, it’s a relatively young system with a massive user base, billions of queries daily, and many billions of indexed documents – with thousands being added every second. On the ranking side, the combination of realtime and social requires new solutions to relevance estimation for newly-created documents, blending different types of live content, evaluation in the absence of direct user feedback, and more. On top of this, the dynamic nature of a nascent company and product leads to a multitude of operational challenges and opportunities. In this talk, I’ll cover some of these challenges and how we approach them at Twitter. “
After the key-note and coffee break the delegates could choose between three industry sessions and sessions on Digital Libraries chaired by Nicola Ferro, Efficiency chaired by Andrew Trotman and IR Theory chaired by Norbert Fuhr, respectively. The industry sessions were on Structure, Global Search Engines and eCommerce and Product Search, chaired by David Carmel & Thijs Westerveld.
The Conference was concluded by Maarten de Rijke, who highlighted some of the facts about the conference. Finally the torch was handed over to Andreas Rauber who introduced the conference location for ECIR 2015, which will take by the beautiful blue Danube in Vienna, Austria.
ECIR2014 was a very inspiring, informative and enjoyable event. The organisers did a great job to make this event a huge success!