In current web applications, more businesses are gradually publishing their business as services over the web. This growing number of web services available within an organization and on the Web raises a new and challenging search problem: locating desired web services. Searching for web services with conventional web search engines is insufficient in this context. Automatically clustering Web Service Description Language (WSDL) files on the web into functionally similar homogeneous service groups can be seen as a bootstrapping step for creating a service search engine and, at the same time, reducing the search space for service discovery. In order to overcome some the limitations of pattern-matching approach, the proposed work uses two semantic approaches to cluster similar services. An experimental study based on an information retrieval technique known as latent semantic analysis is applied to the collection of WSDL files and the another semantic approach is based on WordNet which is a lexical database to cluster similar services, as a predecessor step to retrieve the relevant Web services for a user request by search engines. The baseline approach and the two approaches based on semantic is applied on a collection of WSDL documents consisting of to test the quality of clusters formed. As a result, WordNet based approach for clustering shows better cluster quality.