Designing an interactive open-domain question answering system
Natural Language Engineering
| Hi-index | 0.00 |
In moving from factoid Question Answering (QA) to answering complex questions, it has become apparent that insufficient attention has been paid to the user's role in the process, other than as a source of one-shot factual questions or at best a sequence of related questions. Users both want to, and can do, a lot more: With respect to answers, users can usually disambiguate between a range of possible factoid answers and/or navigate information clusters in an answer space; In the QA process itself, users want to ask a wider range of question types, and respond to the system's answer in more ways than with another factual question. In short, real users demand real-time interactive question and answer capabilities, with coherent targeted answers presented in context for easy inspection. Repeat users will require user models that treat information already provided as background to novel information that is now available. Such developments move the paradigm of QA away from single question, single answer modalities, toward interactive QA, where the system may retain memory of the QA process, and where users develop their understanding of a situation through an interactive QA dialogue. Dialogue systems already allow users to interact with simple, structured data such as train or flight timetables, using a dialogue component based on variations of finite-state models. These models make intensive use of the structure of the domain to constrain the range of possible interactions. The goal of this two day workshop is to explore the area of dialogue as applied to the QA scenario, to extend current technology beyond factoid QA. We would like the workshop to produce some tangible output, which at the very least will be a blueprint for future development of the field. Each of the keynote speakers will add something to the discussion about the future direction (or past developments) of interactive QA. During these presentations, and the presentations of the participants, notes will be taken about research priorities, existing systems, methodologies and principles. At the end of the workshop, there will be a discussion section to produce a roadmap for the future development of interactive QA systems. This roadmap will be circulated to participants after the event.