Semantic Web Services (SWS) has been an active research topic in the recent years. It aims toachieve automatic Web service discovery, and invocation and composition of services, by addingsemantics to the services, which is very significant for accelerating the achievement of Serviceorientedarchitectures by solving a lot of interoperability issues. Geospatial data on the Webcontains more and more important information. Capturing, analyzing and managing such data canhelp people to achieve various kinds of tasks. Discovery of Semantic Web Services in Geospatialdomain is therefore significant. Nowadays the existing semantic Web service discovery frameworksin geospatial domain have either complex interface or require extra knowledge (for instance, theWeb Service Modeling Language (WSML) to be able to provide correct queries.This thesis suggests an Ontology Based Natural Language Discovery of Semantic Web Services(ONALDIS). ONALDIS works generally in the geospatial domain, and offers a command lineinterface which takes natural language questions as input, and gives a WSML query as output. ThisWSML query can be further processed by an existing SWS discovery framework to discoversemantic Web services. ONALDIS achieves the mapping between natural language query andWSML query by analyzing domain ontologies with some rules and generates word sets and WSMLqueries from the ontologies.In this thesis, semantic Web services and geospatial domain are first introduced. The SWINGsystem and the need for a natural language interface are then discussed. Some existing approachesfor natural language interfaces, mainly Question Answering (QA) systems are presented. Further,ONALDIS is introduced as a solution of a natural language interface for semantic Web servicediscovery in the geospatial domain, with an implementation for the SWING system. Finally, theconclusions are presented and further work is suggested.