File size: 1,381 Bytes
dc78b20 |
1 |
question answering based on semantic structures the ability to answer complex questions posed in natural language depends on (1) the depth of the available semantic representations and (2) the inferential mechanisms they support. in this paper we describe a qa architecture where questions are analyzed and candidate answers generated by 1) identifying predicate argument structures and semantic frames from the input and 2) performing structured probabilistic inference using the extracted relations in the context of a domain and scenario model. a novel aspect of our system is a scalable and expressive representation of actions and events based on coordinated probabilistic relational models (cprm). in this paper we report on the ability of the implemented system to perform several forms of probabilistic and temporal inferences to extract answers to complex questions. the results indicate enhanced accuracy over current state-of-the-art q/a systems. we explore the role of semantic structures in question answering. we demonstrate that question answering can stand to benefit from broad coverage semantic processing. our question answering system takes propbank/framenet annotations as input, uses the propbank targets to indicate which actions are being described with which arguments and produces an answer using probabilistic models of actions as the tools of inference. |