其他知识库

With the rapid growth of resources, how to make massive literature retrieval effectively has become a problem to be solved. In this paper, we mainly introduced and analyzed the retrieval methods, such as the parallel retrieval, the distributional retrieval, the semantic retrieval and the parallel massive data retrieval. In addition, we also gave the advantages and disadvantages of them. Through the analysis and research, we find that the semantic search based on cloud computing has advantages in terms of accuracy, but the distributed retrieval and the parallel massive retrieval based on Map/Reduce can have higher efficiency. We hope to find a method that can balance the accuracy with efficiency through combine the existing methods.