Abstract
Reading Comprehension is a task that is sufficiently close to information extraction applications such as question answering. A reading comprehension (RC) system attempts to understand a docu-ment and returns an answer sentence when posed with a question. This paper proposes an RC system which utilizes different tech-niques, including pattern matching, semantic relation inference and the context assistance rule set. This approach gave improved RC performances for the Remedia corpus. We give the deep perform-ance analysis across the experimental results, such as the perform-ance impact by different techniques, performance impact by the technique of co-reference resolution, and we also ran pairwise t-tests that show the significance on performance improvements.