The STUDIA UNIVERSITATIS BABEŞ-BOLYAI issue article summary

The summary of the selected article appears at the bottom of the page. In order to get back to the contents of the issue this article belongs to you have to access the link from the title. In order to see all the articles of the archive which have as author/co-author one of the authors mentioned below, you have to access the link from the author's name.

  
       
         
    STUDIA INFORMATICA - Issue no. Sp.Issue 1 / 2009  
         
  Article:   COMPACTING SYNTACTIC PARSE TREES INTO ENTITY RELATIONSHIP GRAPHS.

Authors:  PÉTER SZILÁGYI. 		 
       
         
  Abstract:   At the moment computers are only able to extract useful information from natural language using known patterns, reason for which they can only reach the tip of the information iceberg contained within the texts. To gain more information, shallow parsing techniques are no longer powerful enough, other methods are needed, which can execute deep parsing on the texts to determine the semantic elements and their relationships. A new approach is introduced, with which the result of syntactic parsers canbe further processed to create a graph that is much more tractable for computer programs. This goal was achieved in the following three steps: the enrollment ofthe words of the text into important semantic categories; the extraction of the relationships between the categorized words using syntactic rules based on the syntactic parse tree; and the disambiguation of multi-sense relationships using aprobabilistic model constructed with maximum entropy.

Key words and phrases. syntactic parser, semantic parser, maximum entropy. 		 
         
     
         
         
      Back to previous page