實驗室成員‎ > ‎

陳明彥

陳明彥 Ming-Yen Chen

博士論文 (2009)

語意感知之多意圖資訊檢索機制研發
Research and Development of a Semantic-Aware Mechanism for Multipurpose Information Retrieval

關鍵字 Keywords

多意圖資訊檢索, 資訊檢索, 語意感知
semantic aware, multipurpose information retrieval, information retrieval

摘要

知識經濟時代的來臨使得知識變成個人與組織最重要的資產,也成為決定企業競爭力的關鍵要素。資訊為一知識的載體,隱含人類欲與他人溝通與傳遞之知識內容,故一有效率的資訊檢索機制將可達成知識分享與再用的目標。現有之資訊檢索機制大多以關鍵字檢索為主,以關鍵字為基礎進行比對替檢索者搜尋所需內容。以關鍵字進行檢索雖然易於實施與使用,但不易完整呈現查詢與內容中之語意特徵,故易導致檢索錯誤的情況。 在以文字為基礎的內容中,作者欲表達的意圖與概念會透過字詞與邏輯的組合,以人類可理解的語意呈現。故若能透過以語意為基礎的方式進行知識內容的檢索,將可有效提升知識內容的通透性與能見度,引導內容的作者及使用者以語意為基礎進行無縫地溝通及互動,進而使知識內容得以正確、快速地傳遞至使用者手中。 本研究提出ㄧ語意感知之多意圖資訊檢索機制,透過對內容語意的處理、識別、擷取、擴張與比對等程序,達成以下目的:(1) 分析與辨別資訊內容中的語意特徵、(2) 發展一可呈現資訊內容語意特徵,並將語意特徵結構化與具體化的語意圖像、(3) 設計一多意圖資訊檢索機制,可根據不同類型的使用者及其使用需求,提供不同的檢索模式。本研究提出之語意感知機制可改善傳統以關鍵字為主之資訊檢索模式,令使用者可透過一語意感知的查詢與檢索方式獲取其所需資訊,進而提昇資訊內容的分享與再用性。

Abstract

In recent years, knowledge becomes the most important asset of individuals as well organizations, and also determines the competitiveness of an enterprise. Information content is a knowledge container that implies what human beings transform their knowledge in when they want to communicate with other people. Therefore, effective information content retrieval can achieve the goal and value of knowledge sharing and reusing. The existing information retrieval systems are mostly keyword-based and retrieve relevant information content by matching keywords. Keyword-based search, in spite of its merits of expedient query for information and ease-of-use, has failed to represent the complete semantics contained in the content and has let to the retrieval failure. In a textual content, the author’s intention is represented in a semantic format of various combinations of word-word relations that are comprehensible to human beings. Accordingly, retrieving information content from a semantic approach can effectively improve transparency and visibility of the content and guide both the content creator and the content user to engage in seamless, semantic-based communications and interactions. This study developed a semantic-aware mechanism for multipurpose information retrieval that handles the processing, recognition, extraction, extensions and matching of content semantics to achieve the following objectives: (1) to analyze and determine the semantic features of information content; (2) to develop a semantic pattern that represents semantic features of the content, and to structuralize and materialize semantic features; (3) to design a multipurpose information retrieval model that provides the most appropriate retrieval method for different types of users depending on their needs. This mechanism is capable of improving the traditional problem of keyword search and enables the user to perform a semantic-aware query and search for the required information, thereby improving the reusing and sharing of information content.


Comments