Treffer: SNERC: Enhancing Knowledge Management with Named Entity Recognition and Document Classification for Apply Gaming.

In this article, we present Stanford Named Entity Recognition and Classification (SNERC), an intelligent system designed to enhance knowledge management through named entity recognition (NER) and document classification (DC) in the field of Applied Gaming. In this domain, the effective application of NER and DC is essential for addressing information overload (IO), enabling software developers to efficiently search, filter, and retrieve large volumes of textual data from web sources. SNERC streamlines the management and deployment of machine learning (ML)-based NER models, supporting the accurate extraction of named entities (NEs) and the classification of heterogeneous textual documents. The system tackles key challenges in NER, such as the impact of language and domain specificity on model performance, domain adaptation, and the complexity of handling diverse NE types. We demonstrate SNERC's capabilities through real-world use cases, highlighting improvements in DC and information retrieval (IR) within applied gaming scenarios. The system provides core functionalities for training, evaluating, and managing NER models using the Stanford CoreNLP framework. Additionally, SNERC integrates with a rule-based expert system (RBES) to enable the automatic categorization of documents into predefined taxonomies within a knowledge management system. We present results from comprehensive qualitative and quantitative evaluations--measured through precision, recall, and F-score--to assess the system's effectiveness and identify areas for further optimization, supporting seamless integration into real-world operational environments. [ABSTRACT FROM AUTHOR]

Copyright of Artificial Intelligence & Applications (2811-0854) is the property of Bon View Publishing and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)