Browsing by Subject "Knowledge integration"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item Knowledge integration in machine reading(2011-08) Kim, Doo Soon; Porter, Bruce, 1956-; Allen, James F.; Barker, Kenneth J.; Lifschitz, Vladimir; Mooney, Raymond J.Machine reading is the artificial-intelligence task of automatically reading a corpus of texts and, from the contents, building a knowledge base that supports automated reasoning and question answering. Success at this task could fundamentally solve the knowledge acquisition bottleneck – the widely recognized problem that knowledge-based AI systems are difficult and expensive to build because of the difficulty of acquiring knowledge from authoritative sources and building useful knowledge bases. One challenge inherent in machine reading is knowledge integration – the task of correctly and coherently combining knowledge snippets extracted from texts. This dissertation shows that knowledge integration can be automated and that it can significantly improve the performance of machine reading. We specifically focus on two contributions of knowledge integration. The first contribution is for improving the coherence of learned knowledge bases to better support automated reasoning and question answering. Knowledge integration achieves this benefit by aligning knowledge snippets that contain overlapping content. The alignment is difficult because the snippets can use significantly different surface forms. In one common type of variation, two snippets might contain overlapping content that is expressed at different levels of granularity or detail. Our matcher can “see past” this difference to align knowledge snippets drawn from a single document, from multiple documents, or from a document and a background knowledge base. The second contribution is for improving text interpretation. Our approach is to delay ambiguity resolution to enable a machine-reading system to maintain multiple candidate interpretations. This is useful because typically, as the system reads through texts, evidence accumulates to help the knowledge integration system resolve ambiguities correctly. To avoid a combinatorial explosion in the number of candidate interpretations, we propose the packed representation to compactly encode all the candidates. Also, we present an algorithm that prunes interpretations from the packed representation as evidence accumulates. We evaluate our work by building and testing two prototype machine reading systems and measuring the quality of the knowledge bases they construct. The evaluation shows that our knowledge integration algorithms improve the cohesiveness of the knowledge bases, indicating their improved ability to support automated reasoning and question answering. The evaluation also shows that our approach to postponing ambiguity resolution improves the system’s accuracy at text interpretation.Item An understanding of the capabilities and limitations of technology-based solutions to Child Protective Services : using a knowledge-based and process-oriented mediation model(2010-12) Jang, Kyeonghee; Schwab, A. James; Jarvenpaa, Sirkka L.; Landuyt, Noel G.; Lauderdale, Michael L.; Streeter, Calvin L.One important research direction that has emerged in Child Protective Services (CPS) is the potential of information technology (IT) to be used by CPS agencies in order to enhance organizational effectiveness by addressing the barriers that caseworkers face in integrating multiple stakeholders’ knowledge. Based on empirical findings with regard to numerous unsuccessful IT development initiatives, the present study strives to gain an in-depth understanding of the research question: How can CPS caseworkers be supported by their agency in the integration of knowledge resources, thereby contributing to organizational effectiveness? A literature review to answer this question revealed the following two major research gaps: the adoption of a technology-focused perspective of intervention and the use of direct research models to evaluate this kind of intervention. In order to bridge these research gaps, this study presented a knowledge-based and process-oriented mediation model, built around the concept of knowledge integration that involves related processes at the syntactic, semantic, and pragmatic levels. In this model, a process-oriented Knowledge Management System (KMS) stemming from a Socio-Technical System (STS) perspective was proposed as an alternative intervention model consisting of knowledge management intervention in three dimensions: techno-structural, socio-cultural, and inter-organizational practices. This mediation model partitions the effect of this KMS on outcome (organizational effectiveness) into two components: the direct effect and the indirect effect that is mediated by its output (a CPS caseworker’s knowledge integration ability). This research model was empirically tested using Structural Equation Modeling. This analysis used a sub-set of the 2008 Survey of Organizational Excellence (SOE) data set, which includes the perceptions of CPS caseworkers in the Texas DFPS about their work environment. Results indicate that each of the three dimensions of knowledge management practices enhanced a CPS caseworker’s knowledge integration ability. This ability was a critical factor in determining organizational effectiveness. The mediation effects of a caseworker’s knowledge integration ability were found to mediate the relationship between three dimensions of knowledge management practices and organizational effectiveness. Overall, this mediation model was more useful in explaining the complex relationships among the variables of interest than other direct models.