Click here to Skip to main content
15,881,882 members
Articles / Containers / Virtual Machine

Statistical parsing of English sentences

Rate me:
Please Sign up or sign in to vote.
4.95/5 (88 votes)
13 Dec 200617 min read 985.6K   23.6K   239  
Shows how to generate parse trees for English language sentences, using a C# port of OpenNLP, a statistical natural language parsing library.
using System;
using System.IO;
using SharpEntropy;
using SharpEntropy.IO;

namespace ModelConverter
{
	/// <summary>
	/// Summary description for Converter.
	/// </summary>
	class Converter
	{
		/// <summary>
		/// The main entry point for the application.
		/// </summary>
		[STAThread]
		static void Main(string[] args)
		{
			if (args.Length != 1)
			{
				Console.WriteLine("You need to specify 1 argument - the path of the folder to convert.");
			}
			else
			{
				string modelPath = args[0];

				if (ConvertFolder(modelPath))
				{
					Console.WriteLine("conversion complete");
				}
				else
				{
					Console.WriteLine("conversion failed");
				}
			}
			Console.ReadLine();
		}

		private static bool ConvertFolder(string folder)
		{
			try
			{
				BinaryGisModelWriter writer = new BinaryGisModelWriter();

				foreach (string file in Directory.GetFiles(folder))
				{
					if (file.Substring(file.Length - 4, 4) == ".bin")
					{
						Console.Write("converting " + file + " ...");
						writer.Persist(new GisModel(new JavaBinaryGisModelReader(file)), file.Replace(".bin", ".nbin"));
						Console.WriteLine("done");
					}
				}
			}
			catch (Exception ex)
			{
				Console.WriteLine("Exception occurred: " + ex.Message);
				return false;
			}

			foreach (string childFolder in Directory.GetDirectories(folder))
			{
				if (!ConvertFolder(childFolder))
				{
					return false;
				}
			}

			return true;
		}
	}
}

By viewing downloads associated with this article you agree to the Terms of Service and the article's licence.

If a file you wish to view isn't highlighted, and is a text file (not binary), please let us know and we'll add colourisation support for it.

License

This article has no explicit license attached to it but may contain usage terms in the article text or the download files themselves. If in doubt please contact the author via the discussion board below.

A list of licenses authors might use can be found here


Written By
Web Developer
United Kingdom United Kingdom
Richard Northedge is a senior developer with a UK Microsoft Gold Partner company. He has a postgraduate degree in English Literature, has been programming professionally since 1998 and has been an MCSD since 2000.

Comments and Discussions