整合多種字詞相似度的創新方法

A Novel Approach to Aggregating Various Word Similarity Measures

林宣丞(Hsuan-Chen Lin)

指導教授 ： 李允中

國立臺灣大學/電機資訊學院/資訊工程學研究所/碩士(2016年)

https://doi.org/10.6342/NTU201601632

摘要

近年來，網路服務的數量不斷上升．對於如何組成複雜服務的研究也日新月異．在組成服務的流程中，匹配服務扮演不可或缺的角色．尋找最佳匹配的服務的重要性不可言喻．要找出最適合的服務，在服務文件裡的重要資訊必須被完整地取出．將這些資料放置在良好的架構裡，並將兩個結構的差異量化．運用這些數值可以幫助網路服務匹配提供搜尋結果．接著，文字語意必須納入考量．許多研究著重在不同語意測量方法下對某種任務的表現．整合多種語意的研究並不多見．在此篇論文中，我們提出了一個整合不同語意系統 的框架來計算提出的資訊.此框架是設計用來辨認出服務文件的特色已幫助服務匹配.

關鍵字

WSDL ； OWL-TC ； OWLS-TC ； 服務匹配

並列摘要

In the recent years, the number of web services has risen up swiftly. Numerous works have been done on how to compose services. In the process of composing services, service matching plays an indispensable role. The importance of searching the most suitable service among composition can not be overemphasized. In order to find the best match for a service, the essential information in the service document should be extracted impact. Then the data should be put in a structure that describes the service perfectly. Then the difference between two structures from two service documents should be quantized. By using these values, a proper web service match discovery could offer a search result to the user. To measure the difference, word semantic must be considered. Many works focus on the performance of various measures for different tasks. Rarely do the researchers study on aggregating different measures. In this thesis, we propose a framework which aggregates different semantic measure for data extracted from WSDL. This framework is designed to identify the features in the service document, and use several measures for precisely interpret the difference between both semantic and structure information of two services.

並列關鍵字

WSDL ； OWL-TC ； OWLS-TC ； Service Matching

參考文獻

[5] D. M. Blei. Probabilistic topic models. Communications of the ACM, 55(4):77–84, 2012.

[7] K. W. Church and P. Hanks. Word association norms, mutual information, and lex- icography. Computational linguistics, 16(1):22–29, 1990.

[8] T. Hofmann. Unsupervised learning by probabilistic latent semantic analysis. Ma- chine learning, 42(1-2):177–196, 2001.

[10] T. K. Landauer, P. W. Foltz, and D. Laham. An introduction to latent semantic anal- ysis. Discourse processes, 25(2-3):259–284, 1998.

[11] G. A. Miller. Wordnet: a lexical database for english. Communications of the ACM, 38(11):39–41, 1995.