Exploiting Semantic Proximity for Information Retrieval

In this paper, we propose a method which exploits the semantic proximity of words in unrestricted natural language text to retrieve relevant documents. In order to facilitate this functionality, the system represents the documents and the query in the form of semantically relatable sets (SRS), which are a group of entities demanding semantic relations when the semantic representation of the sentence is ultimately produced. We also devise a method to augment the SRSs to further boost the performance. WordNet is used to deal with different forms of divergence between the query and the documents. In a series of experiments on TREC data, our semantic proximity based retrieval technique yields high precision with improved mean-average-precision in comparison to conventional retrieval techniques.