An Experimental Study of Vietnamese Question Answering System

The development of world wide web calls for how to efficiently exploit the information. Mostly, current search engines return a set of related documents which contain keywords. However, users expect the exact and concrete answer for each question. Therefore, it is necessary to build an automatic question answering system (QA). In this paper, we focus on building a QA for Vietnamese. This task especially becomes more and more difficult because of the lack of available tools for processing Vietnamese text. Based on previous research for English, this paper proposed an implementation for Vietnamese question answering system by combining SnowBall system and semantic relation extraction using search engines. The experimental results on travelling domain proved that this proposed method is sufficient for Vietnamese question answering system. We achieved 89.7% precision and 91.4% ability to give the answers when testing on travelling domain.