Esempio n. 1
0
        private static void Main()
        {
            SummarizedDocument summarizedDocument = Summarizer.Summarize(
                new FileContentProvider(Path.Combine(Path.GetDirectoryName(Assembly.GetExecutingAssembly().Location), "TextualData\\AutomaticSummarization.txt")),
                new SummarizerArguments
            {
                Language            = "en",
                MaxSummarySentences = 5
            });

            string summery = string.Join(Environment.NewLine, summarizedDocument.Sentences);

            Console.Write(summery);
            Console.ReadLine();
        }
Esempio n. 2
0
        private static void Main()
        {
            SummarizerArguments summarizerArguments = new SummarizerArguments
            {
                InputFile = Path.Combine(Path.GetDirectoryName(Assembly.GetExecutingAssembly().Location), "TextualData", "AutomaticSummarization.txt")
            };

            SummarizedDocument summarizedDocument = Summarizer.Summarize(summarizerArguments);

            string summery = string.Join(Environment.NewLine, summarizedDocument.Sentences);

            Console.Write(summery);

            Console.ReadLine();
        }
Esempio n. 3
0
    public static String Summarize(String text)
    {
        var summaryArgs = new SummarizerArguments();

        summaryArgs.DictionaryLanguage = "en";
        //summaryArgs.DisplayLines = 3;
        summaryArgs.DisplayPercent = 50;
        summaryArgs.InputString    = text;


        SummarizedDocument doc = OpenTextSummarizer.Summarizer.Summarize(summaryArgs);
        var output             = doc.Sentences;
        var summary            = string.Concat(output.ToArray());

        return(summary);
    }
Esempio n. 4
0
        private string SummarizeText(string text)
        {
            // Set text summarize arguments
            SummarizerArguments sumargs = new SummarizerArguments
            {
                DictionaryLanguage = "en",
                DisplayLines       = 5,
                DisplayPercent     = 0,
                InputFile          = "",
                InputString        = text
            };

            // Summarize text
            SummarizedDocument doc = Summarizer.Summarize(sumargs);

            // Return result
            return(string.Join("\r\n\r\n", doc.Sentences.ToArray()));
        }
        private void SummarizeButton_Click(object sender, EventArgs e)
        {
            int sentCount = 1;

            int.TryParse(numericUpDown1.Text, out sentCount);
            SummarizerArguments sumargs = new SummarizerArguments
            {
                DictionaryLanguage = "en",
                DisplayLines       = sentCount,
                DisplayPercent     = 0,
                InputFile          = "",
                InputString        = OriginalTextBox.Text
            };
            SummarizedDocument doc     = Summarizer.Summarize(sumargs);
            string             summary = string.Join("\r\n\r\n", doc.Sentences.ToArray());

            SummaryTextBox.Text = summary;
        }
Esempio n. 6
0
        private void button3_Click(object sender, EventArgs e)
        {
            string path = "E:\\Dropbox\\Masters\\myMSc\\PracticalPart\\Sematic_K-MEANSClustering\\MScDataSets\\Reuters21578\\00\\000.xml";
            string path_data_docCollection       = "E:\\Dropbox\\Masters\\myMSc\\PracticalPart\\Sematic_K-MEANSClustering\\MScDataSets\\Reuters21578\\data\\00_" + maxNoDoc + "_docCollection.xml";
            string path_data_mainCLusterNodeList = "E:\\Dropbox\\Masters\\myMSc\\PracticalPart\\Sematic_K-MEANSClustering\\MScDataSets\\Reuters21578\\data\\00_" + maxNoDoc + "_mainCLusterNodeList.xml";


            if (cboxDataSet.Text == "Reu_01")
            {
                path = "E:\\Dropbox\\Masters\\myMSc\\PracticalPart\\Sematic_K-MEANSClustering\\MScDataSets\\Reuters21578\\Reu_01\\reut2-000_small.xml";
                path_data_docCollection       = "E:\\Dropbox\\Masters\\myMSc\\PracticalPart\\Sematic_K-MEANSClustering\\MScDataSets\\Reuters21578\\data\\01_" + maxNoDoc + "_docCollection.xml";
                path_data_mainCLusterNodeList = "E:\\Dropbox\\Masters\\myMSc\\PracticalPart\\Sematic_K-MEANSClustering\\MScDataSets\\Reuters21578\\data\\01_" + maxNoDoc + "_mainCLusterNodeList.xml";
            }
            else if (cboxDataSet.Text == "Re0")
            {
            }
            else
            {
                //this is test ds so already assigned
            }

            if (File.Exists(path_data_docCollection) && File.Exists(path_data_mainCLusterNodeList))
            {
                docCollection.DocumentList = DeSerializeObject <List <string> >(path_data_docCollection);
                mainCLusterNodeList        = DeSerializeObject <List <ClusterNode> >(path_data_mainCLusterNodeList);
            }
            else
            {
                XmlDocument doc2 = new XmlDocument();
                doc2.Load(path);

                XmlNodeList nodelist  = doc2.DocumentElement.SelectNodes("/main/REUTERS");
                int         n         = 1;
                int         sentCount = 5;
                foreach (XmlNode node in nodelist)
                {
                    ClusterNode item = new ClusterNode();
                    item.cLusters = new List <string>();
                    XmlNode body = node.SelectSingleNode("TEXT/BODY");
                    if (body == null)
                    {
                        continue;
                    }
                    string text = body.InnerText;
                    if (body.InnerText.Length > 400)
                    {
                        SummarizerArguments sumargs = new SummarizerArguments
                        {
                            DictionaryLanguage = "en",
                            DisplayLines       = sentCount,
                            DisplayPercent     = 0,
                            InputFile          = "",
                            InputString        = body.InnerText
                        };
                        SummarizedDocument doc     = Summarizer.Summarize(sumargs);
                        string             summary = string.Join("\r\n\r\n", doc.Sentences.ToArray());
                        text = summary;
                        int len = summary.Length;
                    }
                    XmlNodeList nodelistPLACES = node.SelectNodes("PLACES/D");
                    foreach (XmlNode place in nodelistPLACES)
                    {
                        item.cLusters.Add(place.InnerText);
                    }
                    //XmlNodeList nodelistTOPICS = node.SelectNodes("TOPICS/D");
                    //foreach (XmlNode topic in nodelistTOPICS)
                    //{
                    //    item.cLusters.Add(topic.InnerText);
                    //}

                    docCollection.DocumentList.Add(text);
                    item.id      = n;
                    item.content = text;
                    //item.cLuster = cLuster.InnerXml;
                    mainCLusterNodeList.Add(item);
                    n++;
                    if (n > maxNoDoc)
                    {
                        break;
                    }
                }
                SerializeObject(docCollection.DocumentList, path_data_docCollection);
                SerializeObject(mainCLusterNodeList, path_data_mainCLusterNodeList);
            }
            int totalDoc = 0;

            if (int.TryParse(docCollection.DocumentList.Count.ToString(), out totalDoc))
            {
                lblTotalDoc.Text = totalDoc.ToString();
            }
            MessageBox.Show("Done");
        }