s In TREC-10, we participated in the web track (only ad-hoc task) and the QA track (only main task). In the QA track, our QA system (SiteQ) has general architecture with three proc...
Gary Geunbae Lee, Jungyun Seo, Seungwoo Lee, Hanmi...
How do individual HCI-practitioners evaluate their own work practice? And how would they like to evaluate it? Answers to these questions will give new knowledge on the state-of-th...
Compositional question answering begins by mapping questions to logical forms, but training a semantic parser to perform this mapping typically requires the costly annotation of t...
Complex tasks like question answering need to be able to identify events in text and the relations among those events. We show that this event identification task and a related ta...
We develop and evaluate a model of behavior on the Give-N task, a commonly used measure of young children's number knowledge. Our model uses the knower-level theory of how ch...