Spring 2018


Perhaps low recall but high precision at ECIR 2018

Welcome to our Spring 2018 edition of Informer! Knowing the busy lifestyle of our readership, we made this  a compact issue that should quickly get you updated on some of the things going on in the world of search. First things first, ECIR is ranked A in the CORE conference rankings! This is largely due to the effort put in by IRSG committee member Craig Macdonald. Thanks for that! Furthermore, we have forged a closer link with the Information Retrieval journal. Exciting times!

Read more…

ECIR 2018 Conference Review

ECIR 2018 in Grenoble – what a spectacular setting

The 40th edition of European Conference on Information Retrieval, ECIR 2018, was held in the picturesque city of Grenoble, France. The conference was hosted in Minatec, which boasts of a nice view of the Alps right from the conference venue. A perfect weather and central location meant the attendees could indulge in some sightseeing in the post-conference hours. Éric Gaussier (University Grenoble Alpes), Lorraine Goeuriot (University Grenoble Alpes) and Georges Quénot (CNRS) were the general chairs for ECIR 2018.

Read more…

Conference Review: Autumn School for Information Retrieval and Information Foraging 2017

ASIRF Attendees visiting Dagstuhl ruins on arrival day.

The Autumn School for Information Retrieval and Information Foraging (ASIRF) took place at Schloss Dagstuhl in Saarland (a Southwest German state) between October 1st and 6th, 2017. The School covered user- and system-oriented information retrieval (IR), with lectures given by leading researchers in the field—including Norbert Fuhr, a Salton Award winner. ASIRF was attended by 24 students and 8 lecturers, representing 4 continents and 13 countries.

Read more…

Learning word representations with sequential modelling

Word representations have been learned by matrix factorisation methods or methods that optimise for similar goals (Levy et al. 2015). However these methods are limited to exploiting only co-occurrence statistics or bag-of-word features. Nevertheless these methods are usually so computationally efficient that they can be trained with huge corpora that may contain billions of words. As in other bag-of-word models, structural nature of languages does not account for the models’ inferences. We hypothesise that by using structural architectures, specifically recurrent neural networks, derived word representations contain properties learned from the preserved sequential nature of the input text. Read more…

Events Spring 2018

One Day Events

Watch out for our annual Search Solutions event in November!


Algorithms, Automation and News conference. Of interest to members working in the area of search and news. 22–23 May 2018, Munich, Germany. http://algorithmic.news

EEWC 2018: Eighth Enterprise Engineering Working Conference. Of interest to members working in the area of enterprise search. 28 May- 1 June 2018, Luxembourg, Luxembourg. http://ciaonetwork.org/eewc2018

Read more…