skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: From Question Answering to Visual Exploration

Conference ·
OSTI ID:894869

Research in Question Answering has focused on the quality of information retrieval or extraction using the metrics of precision and recall to judge success; these metrics drive toward finding the specific best answer(s) and are best supportive of a lookup type of search. These do not address the opportunity that users? natural language questions present for exploratory interactions. In this paper, we present an integrated Question Answering environment that combines a visual analytics tool for unstructured text and a state-of-the-art query expansion tool designed to compliment the cognitive processes associated with an information analysts work flow. Analysts are seldom looking for factoid answers to simple questions; their information needs are much more complex in that they may be interested in patterns of answers over time, conflicting information, and even related non-answer data may be critical to learning about a problem or reaching prudent conclusions. In our visual analytics tool, questions result in a comprehensive answer space that allows users to explore the variety within the answers and spot related information in the rest of the data. The exploratory nature of the dialog between the user and this system requires tailored evaluation methods that better address the evolving user goals and counter cognitive biases inherent to exploratory search tasks.

Research Organization:
Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
Sponsoring Organization:
USDOE
DOE Contract Number:
AC05-76RL01830
OSTI ID:
894869
Report Number(s):
PNNL-SA-51770; 400470000; TRN: US200702%%392
Resource Relation:
Conference: Proceedings of the ACM SIGIR workshop on Evaluating Exploratory Search Systems, EESS 2006 Workshop., 47-50
Country of Publication:
United States
Language:
English