This paper presents a now method for answer ranking in question answering (QA) track.
本文描述了一种问题回答任务中答案排序的新方法。
QA system contains three main procedures: question understanding, information retrieve and answer extraction.
问答系统中包括三个主要的部分：问题理解，信息检索和答案抽取。
To improve question answering (QA) performance based on real-world web data sets, a new set of question classes and a general answer re-ranking model are defined.
为了改善真实网络数据集上自动问答系统的性能，定义出新的问题类别集合和通用的答案重新排序模型。
Then, this similarity score is used as a new feature for answer ranking in open domain question answering (QA) track.
这种匹配得分被作为新的特征，应用于计算答案的置信度之中。
Then, this similarity score is used as a new feature for answer ranking in open domain question answering (QA) track.
这种匹配得分被作为新的特征，应用于计算答案的置信度之中。
应用推荐