Inter-document similarity is used for clustering, classification, and other purposes within information retrieval. In this thesis, we investigate several aspects of document similarity. In particular, we investigate the quality of several measures of inter-document similarity, providing a framework suitable for measuring and comparing the effectiveness of inter-document similarity measures. We also explore areas of research related to novelty and diversity in information retrieval. The goal of diversity and novelty is to be able to satisfy as many users as possible while simultaneously minimizing or eliminating duplicate and redundant information from search results. In order to evaluate the effectiveness of diversity-aware retrieval functions, user query logs and other information captured from user interactions with commercial search engines are mined and analyzed in order to uncover various informational aspects underlying queries, which are known as subtopics. We investigate the suitability of implicit associations between document content as an alternative to subtopic mining. We also explore subtopic mining from document anchor text and anchor links. In addition, we investigate the suitability of inter-document similarity as a measure for diversity-aware retrieval models, with the aim of using measured inter-document similarity as a replacement for diversity-aware evaluation models that rely on subtopic mining. Finally, we investigate the suitability and application of document similarity for requirements traceability. We present a fast algorithm that uncovers associations between various versions of frequently edited documents, even in the face of substantial changes.

Med rötter i 1970-talets kvinnorörelse, under parollen ”Det personliga är politiskt”, satte konstnären Mary Kelly moderskap, barnafödande och barnomsorg under lupp i samband med sitt verk Post-Partum Document, 1973-1979. För många kvinnliga konstutövare som gjorde sitt bästa för att, via konsten, frigöra sig från sociala roller och nedärvda beteendemönster, möttes hennes initiativ att ge en bild av denna för dem bromsande moderlighet, med förvåning. Mary Kelly delade konceptkonstens politiska patos för en distanserad reflektion över den kulturella diskursen men hon bytte den lingvistiska analysen mot psykoanalysen. Hennes råmaterial var den subjektiva erfarenheten: kroppen, dess rädslor och sexuella drivkrafter samt de institutionella och kulturella konventioner som tillfogades den. Hennes analysmetoder och omfattande teori banade väg för en mer akademisk, socialkonstruktivistisk feminism som gav ringar på vattnet efter att Post-Partum Document premiärvisades i London år 1976. I linje med den västerländska andra vågen-feminismen utforskade hon den kvinnligt levda erfarenheten men Post-Partum Document markerar också en vändpunkt mot en subjektiv psykoanalys i konstpraktik och teori, som inte minst den efterföljande tredje generationens feminister anammade under 1980-talet. Med verket, som består av sex sektioner och totalt 135 objekt, syftar Mary Kelly till att synliggöra hur den biologiska skillnaden mellan kön och sociala normer befästs via moderskapet och den barnomsorg som det medför. Verket beskriver hennes egen sons socialiseringsprocess fram till sex års ålder. Begreppet Post partum betyder ”efter förlossningen” och syftar till att beskriva moderns tillstånd efter barnets födelse. Denna term gäller således inte barnet vilket också bör understrykas i relation till verkets titel. PPD:s syfte är främst att beskriva modern och hennes känslor i form av oro, rädsla, makt och åtrå i relation till barnet. Modern representerar här samhället, kolonisatören, som tar det anspråkslösa, primitiva spädbarnet till sin barm i syfte att uppfostra det och ge det verktyg för att göra sig förstådd. I Post-Partum Document är hon, till skillnad från psykoanalysens teorier om fallos och kvinnans brist i relation till mannen eftersom hon inte utrustats med penis, ägare av den symboliska fallosen medan mannen, i detta fall sonen, är i underläge. Att Mary Kelly samtidigt bearbetade sin egen erfarenhet av sina respektive roller – som kvinna, konstnär, feminist och sedermera mor - samt polemiken dem emellan gjorde verket unikt i en samtid där konceptkonsten sällan adresserade subjektiva upplevelser medan feministerna, å sin sida, var upptagna med att frigöra sig från de roller som ansågs traditionellt feminina. Via differentierande uttryck av moderns känsloregister i relation till barnet tecknar konstnären en bild av ett moderskap fyllt av oro, nervositet, tvivel, upprymdhet och åtrå samtidigt som hon ställer frågor om föreställningen kring den naturliga modern och kvinnlig sexualitet.

Observations of textual document management by individuals and organizations have suggested the popularity of using categories (e.g., folders) to organize, archive and access documents. The document grouping behavior is intentional acts, reflecting a user¡¦s preferential perspective on semantic coherency or relevant groupings between subjects. Although becoming less adequate as new documents are accumulated, the existing category set or hierarchy may preserve to some extent the user¡¦s preferential perspective on document grouping. Thus, when deriving a new category set or hierarchy, the category set or hierarchy previously established by the user (i.e., semantic coherency of the documents embedded in the existing category set or category hierarchy) should be taken into consideration. In this study, we have proposed an evolution-based technique, Category Hierarchy Evolution (CHE), for managing category hierarchy rather than category set. Specifically, in CHE, the overall similarity between two documents is measured not only by their content similarity but also by their location similarity in the existing category hierarchy. Our empirical evaluation results suggest that the proposed CHE technique outperformed the discovery-based technique (i.e., the traditional content-based document-clustering technique).

With the emergence and proliferation of Internet services and e-commerce applications, a tremendous amount of information is accessible online, typically as textual documents. To facilitate subsequent access to and leverage from this information, the efficient and effective management¡Xspecifically, text categorization¡Xof the ever-increasing volume of textual documents is essential to organizations and person. Existing text categorization techniques focus mainly on categorizing monolingual documents. However, with the globalization of business environments and advances in Internet technology, an organization or person often retrieves and archives documents in different languages, thus creating the need for cross-lingual text categorization. Motivated by the significance of and need for such a cross-lingual text categorization technique, this thesis designs a technique with two different category assignment methods, namely, individual- and cluster-based. The empirical evaluation results show that the cross-lingual text categorization technique performs well and the cluster-based method outperforms the individual-based method.

Text categorization deals with the automatic learning of a text categorization model from a training set of preclassified documents on the basis of their contents and the assignment of unclassified documents to appropriate categories. Most of existing text categorization techniques deal with monolingual documents (i.e., all documents are written in one language) during the text categorization model learning and category assignment (or prediction). However, with the globalization of business environments and advances in Internet technology, an organization or individual often generates/acquires and subsequently archives documents in different languages, thus creating the need for cross-lingual text categorization (CLTC). Existing studies on CLTC focus on the prediction-corpus translation-based approach that lacks of a systematic mechanism for reducing translation noises; thus, limiting their cross-lingual categorization effectiveness. Motivated by the needs of providing more effective CLTC support, we design a training-corpus translation-based CLTC approach. Using the prediction-corpus translation-based approach as the performance benchmark, our empirical evaluation results show that our proposed CLTC approach achieves significantly better classification effectiveness than the benchmark approach does in both Chinese

Documents are records of activities and related knowledge generated from organizational operations. With the trend of more and more documents being stored in the digital form, how to manage this knowledge has become an important issue. The first step is to manage knowledge is to activate the content of knowledge. These documents stored in an organization can not only be retrieved for future reference but also be analyzed to assist managers in making the right decision. Therefore, it is important for a organization to develop document-driven DSS that can discover useful knowledge from a large amount of documents in an organization. Most previous research on document management are focused on the indexing, retrieval and mining of documents, few applications have investigate how this technology can be used to construct knowledge for decision support. The purpose of this research is to propose an approach for developing document-driven DSS. In particular, the research proposes a methodology that combines ontology, indexing, and information retrieval technology to develop event scheme that can be used as a basis for the document-driven DSS. A prototype system has been designed to analyze documents collected from a journal ranking exercise to demonstrate the feasibility of the proposed approach.

Knowledge is an increasingly important asset for organizational competition. In order to manage organizational knowledge effectively, document management is the first step. Therefore, how to manage organizational documents is an issue of interest to many enterprises. In order to manage documents effectively on the computer, it is necessary to understand the content of these documents, which needs a clear description of the included concepts. Ontology is a method for describing concepts and their relations and the metadata of factual data to help users understand the knowledge in a document. Ontology can also be a bridge for knowledge exchange between the user and the computer. Therefore, the construction of ontology is important for knowledge and document management. This research proposes a method for the construction of event ontology, which can be used to construct the ontology of an event. The method includes text pre-processing and event ontology construction. Test pre-processing module includes POS tagger, word filter, and term analysis. Event ontology module provides a friendly editing environment for the user to build the concepts and attributes of an event to provide the ontology of ¡§who,¡¨ ¡§what,¡¨ ¡§where,¡¨ and ¡§what object.¡¨ To verify the feasibility of the proposed method, a prototype system for ontology construction is built. The Alexander Poison Event was used as an example to demonstrate the value of the prototype system.

With the rapid emergence and proliferation of Internet and the trend of globalization, a tremendous number of textual documents written in different languages are electronically accessible online. Efficiently and effectively managing these textual documents written different languages is essential to organizations and individuals. Although poly-lingual text categorization (PLTC) can be approached as a set of independent monolingual classifiers, this naïve approach employs only the training documents of the same language to construct to construct a monolingual classifier and fails to utilize the opportunity offered by poly-lingual training documents. Motivated by the significance of and need for such a poly-lingual text categorization technique, we propose a PLTC technique that takes into account all training documents of all languages when constructing a monolingual classifier for a specific language. Using the independent monolingual text categorization (MnTC) technique as our performance benchmark, our empirical evaluation results show that our proposed PLTC technique achieves higher classification accuracy than the benchmark technique does in both English and Chinese corpora. In addition, our empirical results also suggest the robustness of the proposed PLTC technique with respect to the range of training sizes investigated.

No description available.

RESEARCH INTO KNOWLEDGE MANAGEMENT AND ELECTRONIC GOVERNMENT Based upon official-document electronic operation of Kaohsiung City THESIS ABSTRACT To keep pace with the booming development of high tech and international tendency of globalization, every government makes continuing efforts to the promotion of e-government to facilitate the transformation of government. The goal of our government is to achieve ¡§service modernization¡¨ and ¡§management knowledge formation¡¨. The full employment of information and communication technology doesn¡¦t only lift the administrative efficiency and innovate the service of government but promote the quality of residents¡¦ convenience service, support the reengineering of government and march toward popular intellectual government. Nowadays, the electronic operation has gone through G2G but G2B and G2C are still under way. This thesis only puts the emphasis of research on G2G. Official-document electronic operation more than manifests the efficiency of administrative authorities for the involvement of ¡§management knowledge formation¡¨ in G2G. Official-document electronic operation introduces the concept of knowledge management, builds digital administrative system of knowledge, by means of the steps of knowledge acquisition, knowledge storage, knowledge sharing, knowledge application for knowledge management activities, strives to increase the working efficiency of organization, promote the productivity, upgrade the performance, add the values of knowledge government employees and public, create the long-term advantages of competition for governmental organizations to pursue higher quality of residents¡¦ convenience service and innovative operation of organization. This thesis focuses on Kaohsiung City to conduct study. Through the close combination with knowledge management activity, the correct knowledge is conveyed to knowledge government employees to help them adopt the correct action for the promotion of organizational performance. The major key to the solution of problem is dynamic spirit of learning, aided by motivation system to set up knowledge sharing, getting rid of private treasure and cultivating the sharing wish, building human-based, team work and lifelong learning ideas in order to construct the integrated system of administrative core value, implement the training system of knowledge government employees, cultivate the dynamic service spirit of knowledge government employees and actively provide the information and service of government to the public. Execute the strategy to fully combine with ¡§technology¡¨ and ¡§humanity¡¨, simplify the process of administrative operation, concurrently pursue the performance and human needs to seek the higher quality of residents¡¦ convenience service and innovative operation of organization. Center on ¡§customer orientation¡¨, base upon ¡§performance evaluation¡¨, ¡§democratic concern¡¨ and ¡§lifelong learning¡¨, develop the loyalty to administrative organization and concern for the public and intensify the centripetal force on the government, motivate the dynamic spirit of service and responsible sense toward official duties and attain the common goal of ¡§residents¡¦ convenience¡¨ and ¡§administrative team of customer-oriented service¡¨.