Research On The Construction Of Multi-source Encyclopedic Knowledge Based In Uyghur On Crowdsourcing

With the continuous development of the “The Belt and Road”,exchanges between various ethnic groups are increasing.Xinjiang as a gathering place for minorities,and strengthening the processing of information and characters in ethnic minorities,especially Uygurs is great significance for economic development and information security in Xinjiang.Uyghur language knowledge base,as an indispensable basic resource in Uyghur natural language processing technology,is widely used in various aspects.The construction of the existing Uyghur language knowledge base almost depends on linguistic experts.Although there are accurate and precise,but the construction period is too long and the scale is difficult to expand.With the continuous development of computer technology and the rapid spread of the Internet,there generated massive network text information at the same time.And it was impossible to use the existing knowledge resources to implement the dynamic update of the knowledge base.If the construction of the Uyghur knowledge base can integrate existing Uighur resources and use crowdsourcing methods to divide the tasks into the vast majority of Internet users.And use the power of the majority of Internet users to solve problems in the construction of Uighur language knowledge base.Therefore,this article explores new ways to construct Uighur language resources,and proposes a Uyghur language multi-source encyclopedia knowledge base that integrates existing structured lexicons and network semi-structured Uyghur language resources.First of all,this article elaborates the research background and significance of the project,analyzes the status quo of Uyghur language knowledge base and crowdsourcing application,and proposes the research content and innovation points of this article.Secondly,this paper describes the multi-knowledge source fusion steps in detail,and constructs a Uyghur encyclopedia knowledge base classification system,analyzes Uighur’s existing knowledge resources,and integrate more valuable Uyghur dictionary resources and semi-structured network corpus resources.It is formed Uygur language multi-source encyclopedia of knowledge base prototype preliminary.Then,this article explains the crowdsourcing concept and working mode,it analyzes two important problems about the application of crowdsourcing quality control and incentive mechanism,and it proposes methods of quality control and incentive mechanism to ensure platform quality and performance.Next,this paper designs the crowdsourced platform for Uyghur multi-source encyclopedia knowledge base.Through the overall design of the platform,needs analysis,database design and process design and other steps to achieve the purpose,and describes in detail the technology used in the implementation of the platform and the realization of the platform.Finally,the content of this paper is summarized,and based on the problems and deficiencies in the crowdsourced platform of Uyghur multi-source encyclopedia knowledge base,the future research direction is proposed,exploring the application prospect of crowdsourcing technology and multi-knowledge source fusion in the construction of Uyghur encyclopedia knowledge base.