Creating more fine-grained annotated data than previously relevent document sets is important for evaluating individual components in automatic question answering systems. In this...
In this work we show how interactivity in a voice-enabled question answering application may improve speech recognition. We allow the user to provide a target named entity before ...
The TREC 2004 Question Answering track contained a single task in which question series were used to define a set of targets. Each series contained factoid and list questions and ...
Definition questions represent a largely unexplored area of question answering--they are different from factoid questions in that the goal is to return as many relevant "nugg...
With the ever-increasing amount of textual information available, it is becoming increasingly unlikely that a single document will provide the answer to a question. A more likely ...