Named Entity Extraction and Knowledge Base Enhancement
Loading...
Date
item.page.authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Past decade witnessed an explosive growth in the amount of unstructured data, especially in the
newlinepublic domain, mainly due to Web 2.0 and social media. This has created a need for applications that
newlineextract structured information from such noisy data. Automatic extraction of structured information
newlinefrom unstructured data is called information extraction. Structured information thus extracted is stored
newlinein a Knowledge Base. The knowledge base stores facts about entities like name, type and other attributes.
newlineOn the one hand, the information extraction task utilizes the facts of the entity stored in knowledge base
newlineto refine the extraction process, while on the other, the facts extracted refines the knowledge base facts
newlinefurther. Thus knowledge base provides structure and guidance to the extraction task, and gets enhanced
newlineby the results of the extraction task. Here we see that the tasks of entity extraction and knowledge base
newlineenhancement are mutually dependent and mutually beneficial. Hence this thesis proposes methods to
newlineenhance both the tasks, in an effort to build a strong and sound named entity extraction system.
newlineDocuments typically talk about multiple named entities. All the named entities mentioned in the
newlinedocument are not equally important to the content of the document. Named entities that are important
newlineto the document are called salient named entities. In this thesis we propose a method to identify salient
newlinenamed entity of the document. Importance of a named entity can also be judged by understanding how
newlinethe named entity is semantically related to other named entities mentioned in the document. We propose
newlinea method to identify the presence of such semantic relations within named entities. For example, semantic
newlinerelation like attribute or category in a product title. Understanding the salience of a named entity
newlineand its semantic relations help the Named Entity Extraction task in extracting the important information
newlinefrom text, while filtering out unimportant information.
newlinePerformance of Named Entity Extraction methods de