A news story categorization system

Abstract

This paper describes a pilot version of a commercial application of natural language processing techniques to the problem of categorizing news stories into broad topic categories. The system does not perform a complete semantic or syntactic analyses of the input stories. Its categorizations are dependent on fragmentary recognition using patternmatching techniques. The fragments it looks for are determined by a set of knowledge-based rules. The accuracy of the system is only slightly lower than that of human categorizers.

Micro-Longitudinal Analysis of Web News Updates

“…For example, Makkonen et al [21] categorize news based on shared events which are identified through co-occurrence topic detection and a developed ontology. Summary generation can reference pre-established categories [15], or attempt to develop new categories as current events get processed [1]. Other researchers use information retrieval methodologies to summarize data from multiple websites into one meta-site, allowing a user to go to one place to access news stories pulled from various sources [24,26].…”

Noun retrieval effect on text summarization and delivery of personalized news articles to the user’s desktop

“…These techniques transform the original problem to a simpler one: ranking sentences according to their salience or likelihood of being part of a summary, concatenating them at a second stage. Some techniques [7] try to identify special words and phrases in the text, while in [11] the authors compare patterns of relationships between the sentences.…”

Editorial

“…Although rule-based approaches have proved to be effective at this task (Hayes et al 1988), the knowledge engineering costs are high, making the unsupervised learning approach of neural network models an attractive alternative. Kohonen's topological maps (Kohonen 1990) in particular, have the property that learned categories can be mapped to a two dimensional grid, raising the possibility of constructing a visual interface to the semantic space of a clustered document set (Lin et al 1991).…”