Aim and Scope

Services and users of multilingual IR systems continue to evolve, with many new factors and trends influencing the field. E.g., we are moving to a situation in which there is no longer a single dominant language in which most online information is captured and, with the advance of broadband access and the evolution of both wired and wireless connectivity, users are not just information consumers, but also producers. Text now comes in many shapes—user generated, with low publishing threshold, heavily contextualised, often code switching and multi-lingual, and under little or no editorial control, changes the scene for much of the processing frameworks we previously have been able to assume: blogs, discussion forums, comments left behind on news sites, IM, SMS, Twitter—many new formats for textual interaction carry valuable and timely information, which needs specific tools for processing.

The expectations and habits of users are constantly changing, together with the ways in which they interact with content and services, often creating new and original ways of exploiting them. The use of national languages on global networks is increasing rapidly and language barriers are no longer seen as impossible to overcome but there is growing dissatisfaction with technologies currently available to realize this. As they live ever larger parts of their life online, users need to be able to co-operate and communicate in a way that crosses language boundaries and goes beyond simple translation from one language to another. Users are very diverse in their interpretations of what a query means to them—this issue of interpretation is amplified when crossing language boundaries where the cultural context and norms behind a language have to be taken into account. Interestingly, this issue gives rise to a new type of user need in the setting of large volumes of dynamically changing user generated content: needs for subjective information (“What do people think about …?” and “How do people respond to …?”)

If we are to continue advancing the state-of-the-art in multilingual information access technologies, we need to understand a new breed of users, performing different kinds of tasks within varying domains, often acting within communities to find and produce information not only for themselves, but also to share with other users. This calls for a re-orientation of methodology and goals in the evaluation of multilingual information access systems. We need to study and evaluate multilingual issues from a communicative perspective rather than a purely translational one. Clearly, data is a critical resource for these aims—how to obtain it?

The goal of the workshop is to discuss and start understanding and improving the multilingual user experience. How can we move evaluation of multilingual information access (MLIA) systems beyond system benchmarking in the Cranfield/TREC-style tradition to assessing system effectiveness within today’s operational task contexts? Among other things, the workshop will explore the idea of “multilingual living laboratories” in which to conduct user studies at scale, where infrastructure and instruments for capturing user activity are created. The workshop will be organized around four key dimensions: (multilingual) content, (multilingual) users, (multilingual) tasks and (multilingual) evaluation methodology.

Topics for Discussion

Relevant topics for the MLIA-CULT 2010 include, but are not limited to:

• Proposals for, or experiences with, living laboratories for retrieval evaluation
• Evaluation of MLIA systems via user-centric tasks;
• User & usability indications for multilingual access;
• Analysis of the impact of multilingual/multicultural differences on interface/search design;
• Evaluation and exploitation of contextual information retrieval and multilinguality;
• Evaluation protocols for taking part in the creation of collaborative MLIA experiments;
• Requirements for MLIA systems evaluation by stakeholders (search engines, enterprise portals, digital libraries, …);
• Evaluation of information access on multilingual, user-generated, and fragmentary content;
• Multilinguality in social media and relevant application communities, such as the digital library one;
• Infrastructures and frameworks for supporting, automating, and cooperating in MLIA systems evaluation.

Format

Two types of papers are solicited:

• long papers: 8 pages max;
• short papers: 4 pages max.

Workshop Outcomes

Important Dates

• Submission Deadline: Friday 12nd February 2010
• Notification of Acceptance: Friday 26th February 2010
• Camera Ready: Wednesday 10th March 2010
• Workshop: Sunday 28th March 2010.

Programme Committee

Contacts