• Corpus ID: 14006552

Self-Organizing Maps In Natural Language Processing

  title={Self-Organizing Maps In Natural Language Processing},
  author={Timo Honkela},
Kohonen's Self-Organizing Map (SOM) is one of the most popular arti cial neural network algorithms. Word category maps are SOMs that have been organized according to word similarities, measured by the similarity of the short contexts of the words. Conceptually interrelated words tend to fall into the same or neighboring map nodes. Nodes may thus be viewed as word categories. Although no a priori information about classes is given, during the self-organizing process a model of the word classes… 

Figures from this paper

Self-organizing Maps in Web Mining and Semantic Web
This chapter presents how the self-organizing map (SOM) model can be applied in Web mining, and how a more complex SOM based unsupervised neural network model is used for enriching a domain ontology.
Self-organizing Maps in Web Mining and Semantic Web 357 Self-organizing Maps in Web Mining and Semantic Web
This chapter presents how the SOM model can be applied in Web mining, by giving sets of documents as input data space for SOM and how a more complex SOM based unsupervised neural network model is used for enriching a domain ontology.
Discovering Web Document Clusters with Self-Organizing Maps
The clustering capability of the system allows users to find out quickly what is new in a Web site of interest by co mparing the clusters obtained from the site at different moment s in time.
Analysis of functional similarities of Finnish verbs using the self-organizing map
The results show that even the simple feature selection used in this experiment was found to be suitable for rough automatic categorization of verbs on the basis of data extracted from unrestricted texts and the automatically obtained organization resembles the semantic classification of verbs designed by a linguist.
Uncovering Associations Between DocumentsDieter Merkl
This paper presents the novel La-belSOM method, which automatically selects the most descriptive features of the input patterns mapped onto a particular unit of the map, thus making the associations between the various clusters within the map explicit.
SEMANTIC CLUSTERING OF VERBS Analysis of Morphosyntactic Contexts Using the SOM Algorithm
  • K. Lagus
  • Linguistics, Computer Science
  • 2009
The self-organizing map algorithm is used to visualize and cluster common Finnish verbs based on functional and semantic information coded by case marking and function words like postpositions and adverbs to demonstrate the importance of cultural, social and emotional dimensions in lexical dimensions.
Self-Organising Maps in Document Classification: A Comparison with Six Machine Learning Methods
The self-organising map proved to be yielding the highest accuracies of tested unsupervised methods in classification of the Reuters news collection and the Spanish CLEF 2003 news collection, and comparable accuracies against some of the supervised methods in all three data sets.
A study of the use of self-organising maps in information retrieval
Purpose – The aim of this paper is to explore the possibility of retrieving information with Kohonen self‐organising maps, which are known to be effective to group objects according to their
Corpus analysis and results visualisation using self-organizing maps
This paper addresses the related issues of statistical analysis of text corpora and of intuitively-accessible representation of the results of such analysis, with reference to the Newcastle-Poitiers
Mining massive document collections by the WEBSOM method


Self-Organizing Maps of Document Collections: A New Approach to Interactive Exploration
This article presents a method, WEBSOM, for automatic organization of full-text document collections using the self-organizing map (SOM) algorithm, and presents a case study of its use.
A Practical Approach for Representing Context and for Performing Word Sense Disambiguation Using Neural Networks
A method for representing some context information so that the correct meaning for a word in a sentence can be selected and the development of more powerful context algorithms will be an important topic for future research.
Exploration of very large databases by self-organizing maps
  • T. Kohonen
  • Computer Science
    Proceedings of International Conference on Neural Networks (ICNN'97)
  • 1997
A data organization system and genuine content-addressable memory called the WEBSOM, a two-layer self-organizing map (SOM) architecture where documents become mapped as points on the upper map, in a geometric order that describes the similarity of their contents.
Natural Language Processingwith Modular Neural Networks and Distributed Lexicon
An approach to connectionist natural language processing is proposed, which is based on hierarchically organized modular Parallel Distributed Processing (PDP) networks and a central lexicon of
Engineering applications of the self-organizing map
The self-organizing map method, which converts complex, nonlinear statistical relationships between high-dimensional data into simple geometric relationships on a low-dimensional display, can be utilized for many tasks: reduction of the amount of training data, speeding up learning nonlinear interpolation and extrapolation, generalization, and effective compression of information for its transmission.
A self-organizing semantic map for information retrieval
A neural network’s unsupervised learning algorithm is applied to constructing a selforganizing semantic map for information retrieval, which visualizes semantic relationships between input documents, and has properties of economic representation of data with their interrelationships.
Newsgroup Exploration with WEBSOM Method and Browsing Interface
The WEBSOM method is introduced, which visualizes similarity relations between the documents on a map display, which can be utilized in exploring the material rather than having to rely on traditional search expressions.
Resolving Linguistic Ambiguities with a Neural Data-Oriented Parsing (DOP) System
Comparing Self-Organizing Maps
Two measures for comparing how different maps represent relations between data items are developed, one of which combines an index of discontinuities in the mapping from the input data set to the map grid with a measure of the accuracy with which the map represents the data set.
Lessons Learned in Text Document Classification
This paper takes advantage of the fact that text archives lend themselves naturally to a hierarchical structure by using a hierarchically organized network built up from independent self-organizing maps in order to enable the true establishment of a document taxonomy.