Word sense disambiguation for free-text indexing using a massive semantic network
CIKM '93 Proceedings of the second international conference on Information and knowledge management
Larks: Dynamic Matchmaking Among Heterogeneous Software Agents in Cyberspace
Autonomous Agents and Multi-Agent Systems
A software framework for matchmaking based on semantic web technology
WWW '03 Proceedings of the 12th international conference on World Wide Web
Applied morphological processing of English
Natural Language Engineering
A Framework and Ontology for Dynamic Web Services Selection
IEEE Internet Computing
Structural Semantic Interconnections: A Knowledge-Based Approach to Word Sense Disambiguation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Feature-rich part-of-speech tagging with a cyclic dependency network
NAACL '03 Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - Volume 1
Incorporating non-local information into information extraction systems by Gibbs sampling
ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
Word sense disambiguation: A survey
ACM Computing Surveys (CSUR)
Hi-index | 0.00 |
With the increasing number of available Web services, the need for a sophisticated discovery mechanism becomes essential. Existing UDDI based discovery techniques fail to recognize similarities and differences between Web service capabilities and thus greatly limit the scope of service discovery. Hence, in this paper we present a framework for discovering the vast amount of Web services present in Internet based on a novel semantic approach to automatically discover the most appropriate services to user requirements. Our framework is based on a natural language query to facilitate usage of our implemented discovery framework. For this purpose, we first apply some computational linguistics techniques such as part-of-speech tagging and word sense disambiguation to format and extract useful semantic information from user query. Then, we propose an innovative semantic matchmaking technique based on significant concepts properties in the referenced domain ontology. The proposed technique is implemented in a prototype system to evaluate our system performance and compare it to a related work. The results obtained demonstrate the effectiveness of our approach.