We present two enhanced visualization techniques for the self-organizing map allowing the intuitive representation of input data similarity. The general idea of both approaches is to visualize the relationship of nodes to facilitate the detection of cluster boundaries without modifying the architecture or the basic training process of SOM. One approach mirrors the movement of weight vectors during the training process within a two-dimensional (virtual) output space, whereas the second results in a grid of connected nodes where the intensity of the connection mirrors the similarity of the underlying data items. Both approaches can be combined to allow improved analysis of the inherent structure of high-dimensional input data and an intuitive recognition of cluster boundaries without the necessity of substantial prior knowledge concerning the input patterns. 1 Introduction The self-organizing map allows the mapping of high-dimensional input data onto a two-dimensional output space while...

In this paper we propose an integration of a selforganizing map and semantic networks from WordNet for a text classification task using the new Reuters news corpus. This neural model is based on significance vectors and benefits from the presentation of document clusters. The Hypernym relation in WordNet supplements the neural model in classification. We also analyse the relationships of news headlines and their contents of the new Reuters corpus by a series of experiments. This hybrid approach of neural selforganization and symbolic hypernym relationships is successful to achieve good classification rates on 100,000 full-text news articles. These results demonstrate that this approach can scale up to a large real-world task and show a lot of potential for text classification.

Classification is one of the central issues in any system dealing with text data. The need for effective approaches is dramatically increased nowadays due to the advent of massive digital libraries containing freeform documents. What we are looking for are powerful methods for the exploration of such libraries whereby the discovery of similarities between groups of text documents is the overall goal. In other words, methods that may be used to gain insight in the inherent structure of the various items contained in a text archive are needed. In this paper we demonstrate the applicability of unsupervised neural networks for the task of text document clustering. Specifically, we describe the results from using self-organizing maps for the exploration of document archives. We further argue in favor of paying more attention to the fact that text archives lend themselves naturally to a hierarchical structure. We take advantage of this fact by using a hierarchically organized network built u...

this paper we argue in favor of establishing a hierarchical organization of the document space based on an unsupervised neural network. In much the same way as we are showing the world on dierent pages of an atlas, where each page contains a map showing some portion of the world at some specic resolution, we suggest to use a kind of atlas for document space representation [15,16]. A page of this atlas of the document space shows a portion of the library at some resolution while omitting other parts of the library. As long as general maps that provide an overview of the whole library are available, the user can nd his or her way along the library by choosing maps that provide a suciently detailed view of the area of particular interest. More precisely, we show the eects of using the hierarchical feature map [18] for document archive organization. The distinguished feature of this model is its layered architecture where each layer consists of a number of independent self-organizing maps. The training process results in a hierarchical arrangement of the document collection where self-organizing maps from higher layers of the hierarchy are used to represent the overall organizational principles of the document archive. Maps from lower layers of the hierarchy are used to provide ne-grained distinction between individual documents. Such an organization comes close to what we would usually expect from conventional libraries.

Text archives may be regarded as an almost optimal application arena for unsupervised neural networks. This because many of the operations computers have to perform on text documents are classification tasks based on noisy patterns. As a natural result, an ever increasing number of research reports concerned with that type of application appeared in literature. In this paper we argue in favor of paying more attention to the fact that text archives lend themselves naturally to a hierarchical structure. We take advantage of this fact by using a hierarchically organized network built up from independent self-organizing maps in order to enable the true establishment of a document taxonomy. 1 Introduction The self-organizing map is a neural network model capable of arranging high-dimensional input data within its (usually) two-dimensional output space in such a way that the similarity of the input data is mirrored as faithfully as possible. The utilization of this model is thus especially ...

. Exploratory analysis is an area of increasing interest in the computational linguistics arena. Pragmatically speaking, exploratory analysis may be paraphrased as natural language processing by means of analyzing large corpora of text. Concerning the analysis, appropriate means are statistics, on the one hand, and artificial neural networks, on the other hand. As a challenging application area for exploratory analysis of text corpora we may certainly identify text databases, be it information retrieval or information filtering systems. With this paper we present recent findings of exploratory analysis based on both statistical and neural models applied to legal text corpora. Concerning the artificial neural networks, we rely on a model adhering to the unsupervised learning paradigm. This choice appears naturally when taking into account the specific properties of large text corpora where one is faced with the fact that input-output-mappings as required by supervised learning models ca...