I was invited to talk about issues related to entity ranking, query understanding, and evaluation at the most recent KEYSTONE COST meeting. Here are the slides from my presentation.
krisztianbalog
4M NOK funding from ToppForsk-UiS
I received 4M NOK external funding (~440K EUR) from the ToppForsk programme to work on the FAETE project (From Answering Engines to Task-completion Engines). ToppForsk is a research programme for outstanding young researchers, put in place by the University of Stavanger in cooperation with Universitetsfondet. The official announcement with more details about the programme and its 2015 winners can be found here (in Norwegian). The project, with a total project budget of 9.7M NOK (over 1M EUR), will allow me to spend 60% of my time on research for the following 4 years and will fund 2 PhD students (announcements will follow in due time).
PhD positions in IR
The University of Stavanger invites applications for up to three doctorate scholarships in Information Technology at the Faculty of Science and Technology, in the Department of Electrical Engineering and Computer Science, beginning September 1, 2015.
There are 15 projects offered in total, which include two IR projects supervised by me:
#8. Living labs for information retrieval
Living labs is a new evaluation paradigm for information retrieval (IR), where the idea is to perform experiments in situ, with real users doing real tasks using real-world applications. This type of evaluation is standard practice in (large) industrial research labs, but is only now becoming available to academic researchers [1,2]. Despite recent developments, there are still numerous challenges to be overcome, including living labs architecture and design, hosting, maintenance, security, privacy, participant recruiting, and scenarios and tasks for use development. This focus of this project is on developing and employing the living labs evaluation paradigm for IR. The PhD candidate will contribute to the understanding of online evaluation and how to generalize across different use-cases.
[1] http://living-labs.net/
[2] http://www.clef-newsreel.org/
#9. Answering complex queries
Web search engines have become remarkably effective in providing appropriate answers to queries that are issued frequently. However, when it comes to complex information needs, often formulated as natural language questions, responses become much less satisfactory (e.g., “Which European universities have active Nobel laureates?”). Manual effort is often required to collect and synthesize information from multiple sources, a process that may involve a series of filtering, sorting, and aggregation steps. The goal of this project is to investigate how to improve query understanding and answer retrieval for complex queries, using massive volumes of unstructured data in combination with knowledge bases.
Details and application instructions can be found here.
Application deadline: February 24, 2015.
Important: Feel free to contact me directly for more information regarding the projects. However, applications need to be submitted on jobbnorge.no (i.e., don’t send them in email to me). Also, don’t forget to indicate which projects you are applying for, in order of preference.
Digital exam
The University of Stavanger is one of the higher education institutions in Norway that are now working on a pilot project for digital examination. My web programming and interaction design course will be among the first ones (and the very first one within the Faculty of Science and Technology) that will have a digital exam already this semester.
The latest issue of Teknisk Ukeblad featured an article on this topic where I was also interviewed about my reasons for having a digital, as opposed to paper-based, exam.
The highlighed quote, in free translation, reads like “The point of the exam is that it should be as close to a work situation as possible. Students will not be doing programming on paper when they start their job.” Digital exams also allow for certain websites to be used as reference material, in addition to textbooks.
Living Labs developments
There have been a number of developments over the past months around our living labs for IR evaluation efforts.
We had a very successful challenge workshop in Amsterdam in June, thanks to the support we received from ELIAS, ESF, and ILPS. The scientific report summarizing the event is available online.
There are many challenges associated with operationalizing a living labs benchmarking campaign. Chief of these are incorporating results from experimental search systems into live production systems, and obtaining sufficiently many impressions from relatively low traffic sites. We propose that frequent (head) queries can be used to generate result lists offline, which are then interleaved with results of the production system for live evaluation. The choice of head queries is critical because (1) it removes a harsh requirement of providing rankings in real-time for query requests and (2) it ensures that experimental systems receive enough impressions, on the same set of queries, for a meaningful comparison. This idea is described in detail in an upcoming CIKM’14 short paper: Head First: Living Labs for Ad-hoc Search Evaluation.
A sad, but newsworthy development was that our CIKM’14 workshop got cancelled. It was our plan to organize a living labs challenge as part of the workshop. That challenge cannot be run as originally planned. Now we have something much better.
Living Labs for IR Evaluation (LL4IR) will run as a Lab at CLEF 2015 along the tagline “Give us your ranking, we’ll have it clicked!” The first edition of the lab will focus on three specific use-cases: (1) product search (on an e-commerce site), (2) local domain search (on a university’s website), (3) web search (through a commercial web search engine). See futher details here.