public List <Tag> GetTags(string paragraph)
{
var bin = GetFileStream("en-pos-maxent.bin");
POSModel model = new POSModel(bin);
POSTagger tagger = new POSTaggerME(model);
var sentenceSpans = SentPosDetect(paragraph);
List <Tag> tagsResult = new List <Tag>();
foreach (var sentenceSpan in sentenceSpans)
{
var sentence = sentenceSpan.getCoveredText(paragraph).toString();
var start = sentenceSpan.getStart();
var end = sentenceSpan.getEnd();
var tokenSpans = GetTokens(sentence);
var tokens = new string[tokenSpans.Length];
for (var i = 0; i < tokens.Length; i++)
{
tokens[i] = tokenSpans[i].getCoveredText(sentence).toString();
var tag = tagger.tag(new[] { tokenSpans[i].getCoveredText(sentence).toString() }).FirstOrDefault();
tagsResult.Add(new Tag
{
startIndex = start,
endIndex = end,
category = tag
});
}
}
return(tagsResult);
}
string[] POSTagger(string[] tokens)
{
InputStream modelIn = new FileInputStream(modelPath + "en-pos-maxent.zip");
POSModel model = new POSModel(modelIn);
POSTaggerME tagger = new POSTaggerME(model);
string[] tags = tagger.tag(tokens);
//int i = 0;
//foreach (string s in tags)
//{
// System.Console.WriteLine("{0} : {1}", tokens[i], s);
// debug.Print(tokens[i] + " : " + s + "\n");
// i++;
//}
return(tags);
}
private void button1_Click(object sender, EventArgs e)
{
InputStream modelIn = new FileInputStream("en-pos-maxent.bin");
POSModel model = new POSModel(modelIn);
// initialize POSTaggerME
POSTaggerME tagger = new POSTaggerME(model);
words = textBox1.Text.Split();
String[] result = tagger.tag(words);
label1.Text = "";
for (int i = 0; i < result.Length; i++)
{
label1.Text += result[i] + ", ";
}
}
public override void run(string[] args)
{
if (args.Length != 1)
{
Console.WriteLine(Help);
}
else
{
POSModel model = (new POSModelLoader()).load(new File(args[0]));
POSTaggerME tagger = new POSTaggerME(model);
ObjectStream <string> lineStream = new PlainTextByLineStream(new InputStreamReader(Console.OpenStandardInput));
PerformanceMonitor perfMon = new PerformanceMonitor(System.err, "sent");
perfMon.start();
try
{
string line;
while ((line = lineStream.read()) != null)
{
string[] whitespaceTokenizerLine = WhitespaceTokenizer.INSTANCE.tokenize(line);
string[] tags = tagger.tag(whitespaceTokenizerLine);
POSSample sample = new POSSample(whitespaceTokenizerLine, tags);
Console.WriteLine(sample.ToString());
perfMon.incrementCounter();
}
}
catch (IOException e)
{
CmdLineUtil.handleStdinIoError(e);
}
perfMon.stopAndPrintFinalResult();
}
}
/// <summary>
/// 使用openNLP做英文詞性標註。model: en-pos-maxent.bin。
/// </summary>
/// <param name="tokens">每個需要標註的tokens。</param>
/// <returns>POS array</returns>
public string[] POS(string[] tokens)
{
LoadTagger();
return(tagger.tag(tokens));
}
public String[] getPOS_Tags()
{
String[] result = tagger.tag(words);
return(result);
}
public string[] Chunking(string[] tokens)
{
string[] pos = tagger.tag(tokens);
return(Chunking(tokens, pos));
}
public static IEnumerable<IEnumerable<ChunkItem>> GetChunks(IEnumerable<string> Sentences)
{
var posModelStream = new java.io.ByteArrayInputStream(Resource.en_pos_maxent);//new java.io.FileInputStream(@"C:\dev\d-mill\TextProcessing\OpenNLP\Models\en-pos-maxent.bin");
var posModel = new POSModel(posModelStream);
var pos = new POSTaggerME(posModel);
var modelStream = new java.io.ByteArrayInputStream(Resource.en_token); //java.io.FileInputStream(@"C:\dev\d-mill\TextProcessing\OpenNLP\Models\en-token.bin");
var model = new TokenizerModel(modelStream);
var tokenizer = new TokenizerME(model);
var chunkerModelStream = new java.io.ByteArrayInputStream(Resource.en_chunker);
var chunkerModel = new ChunkerModel(chunkerModelStream);
var chunker = new ChunkerME(chunkerModel);
return Sentences.Select(p => {
var tokens = tokenizer.tokenize(p);
var tags = pos.tag(tokens);
var chunks = chunker.chunk(tokens, tags);
var res = new List<ChunkItem>();
for (var i = 0; i < chunks.Length; i++)
{
res.Add(new ChunkItem { token = tokens[i], tag = tags[i], chunk = chunks[i] });
}
return res;
});
}