Early question and answering (QA) systems focused on keyword search among documents for answers. However, such systems can only answer fact-based questions. It becomes clear that ...
In order for agents and humans to leverage the growing wealth of heterogeneous information and services on the web, increasingly, they need to understand the information that is d...
This paper presents our experiments in question answering for speech corpora. These experiments focus on improving the answer extraction step of the QA process. We present two app...
Unlike simple questions, complex questions cannot be answered by simply extracting named entities. These questions require inferencing and synthesizing information from multiple d...
Scalable information retrieval systems are crucial to meeting the growing volumes of data. We describe work done to facilitate scalability by reducing duplication, providing integ...