Motivation, themes, and goals:
Motivation: There is a growing realisation that relevant information will be increasingly accessible across media and genres, across languages and across modalities. The retrieval of such information will depend on time, place, history of interaction, task in hand, and a range of other factors that are not given explicitly but are implicit in the interaction and ambient environment, namely the context. IR research is now conducted in multi-media, multi-lingual, and multi-modal environments but largely out of context. However, such contextual data can be used effectively to constrain retrieval of information thereby reducing the complexity of the retrieval process. To achieve this, context models for different modalities will need to be developed so that they can be deployed effectively to enhance retrieval performance. Thus truly context-aware and -dependent retrieval will become feasible.
Context implies interactive IR and there may exist a stratification of contexts in association to IR engines and systems. For example, knowing where a user is focusing his or her attention during image retrieval can enhance the operation of relevance feedback to the system. The user's current task situation also acts as context as does his or her current information seeking situation of which IIR forms part. The underlying hypothesis (and belief) is that by taking account of context the next generation of retrieval engines dependent on models of context can be created, designed and developed delivering performance exceeding that of out-of-context engines.
Themes: This workshop will explore a variety of theoretical frameworks, characteristics and research approaches to focus on an agenda of activities to be recommended for future interactive IR (IIR) research. We welcome presentation submissions connected with any aspect of the above, including the following:
- Case studies, user-oriented approaches, simulations, etc. of IR in context
- Contextual IR theory - modeling context, e.g.
- Ontology and knowledge-based IR in context
- Theoretical tools for Information Retrieval in Context (IRiX)
- Evaluation and research methodologies for IRiX
- Usability evaluation
- Interactive IR and interface issues
- Nature of relevance in contexts
- Measures of performance in context and situation-sensitive IR
- The test-collection challenge
- Platforms and frameworks for doing research on IRiX
- IR & DB Integration in context
- Non-content based IR
- Document structure in contextual IR
- Context-sensitive information access
- Algorithmic solutions
- Task-based IIR
- Relevance feedback & query modification issues
- Media and genre-dependent applications
- Cross-media, cross-language and cross-modal approaches
- Personalized and collaborative information access in context
Goal: The Workshop intends to outline a workable agenda for future research on IR in Context by substantiating the variation of characteristics and recommendable approaches dealing with information in context.