本文整理了Java中edu.stanford.nlp.ling.Word.toString()
方法的一些代码示例,展示了Word.toString()
的具体用法。这些代码示例主要来源于Github
/Stackoverflow
/Maven
等平台,是从一些精选项目中提取出来的代码,具有较强的参考意义,能在一定程度帮忙到你。Word.toString()
方法的具体详情如下:
包路径:edu.stanford.nlp.ling.Word
类名称:Word
方法名:toString
暂无
代码示例来源:origin: stanfordnlp/CoreNLP
private static ArrayList<Word> postProcessSentence(ArrayList<Word> sent) {
ArrayList<Word> newSent = new ArrayList<>();
for(Word word : sent) {
if(newSent.size() > 0) {
String prevWord = newSent.get(newSent.size()-1).toString();
String curWord = word.toString();
String prevChar = prevWord.substring(prevWord.length()-1);
String curChar = curWord.substring(0,1);
if(!isChinese(prevChar) && !isChinese(curChar)) {
Word mergedWord = new Word(prevWord+curWord);
newSent.set(newSent.size()-1, mergedWord);
//printlnErr("merged: "+mergedWord);
//printlnErr("merged: "+mergedWord+" from: "+prevWord+" and: "+curWord);
continue;
}
}
newSent.add(word);
}
return new ArrayList<>(newSent);
}
代码示例来源:origin: stanfordnlp/CoreNLP
private void tokenizeDate(String inputDate) {
tokens = new ArrayList<>();
Pattern pat = Pattern.compile("[-]");
if (inputDate == null) {
System.out.println("Null input date");
}
Matcher m = pat.matcher(inputDate);
String str = m.replaceAll(" - ");
str = str.replaceAll(",", " ");
PTBTokenizer<Word> tokenizer = PTBTokenizer.newPTBTokenizer(new BufferedReader(new StringReader(str)));
while (tokenizer.hasNext()) {
Word nextToken = tokenizer.next();
tokens.add(nextToken.toString());
}
if(DEBUG) {
System.out.println("tokens:" + tokens);
}
}
代码示例来源:origin: stanfordnlp/CoreNLP
docStr.append(' ');
docStr.append(aDoc.toString());
代码示例来源:origin: edu.stanford.nlp/corenlp
private void tokenizeDate(String inputDate) {
tokens = new ArrayList<String>();
Pattern pat = Pattern.compile("[-]");
if (inputDate == null) {
System.out.println("Null input date");
}
Matcher m = pat.matcher(inputDate);
String str = m.replaceAll(" - ");
str = str.replaceAll(",", " ");
PTBTokenizer<Word> tokenizer = PTBTokenizer.newPTBTokenizer(new BufferedReader(new StringReader(str)));
while (tokenizer.hasNext()) {
Word nextToken = tokenizer.next();
tokens.add(nextToken.toString());
}
if(DEBUG) {
System.out.println("tokens:" + tokens);
}
}
代码示例来源:origin: com.guokr/stan-cn-com
private void tokenizeDate(String inputDate) {
tokens = new ArrayList<String>();
Pattern pat = Pattern.compile("[-]");
if (inputDate == null) {
System.out.println("Null input date");
}
Matcher m = pat.matcher(inputDate);
String str = m.replaceAll(" - ");
str = str.replaceAll(",", " ");
PTBTokenizer<Word> tokenizer = PTBTokenizer.newPTBTokenizer(new BufferedReader(new StringReader(str)));
while (tokenizer.hasNext()) {
Word nextToken = tokenizer.next();
tokens.add(nextToken.toString());
}
if(DEBUG) {
System.out.println("tokens:" + tokens);
}
}
代码示例来源:origin: edu.stanford.nlp/stanford-corenlp
private void tokenizeDate(String inputDate) {
tokens = new ArrayList<>();
Pattern pat = Pattern.compile("[-]");
if (inputDate == null) {
System.out.println("Null input date");
}
Matcher m = pat.matcher(inputDate);
String str = m.replaceAll(" - ");
str = str.replaceAll(",", " ");
PTBTokenizer<Word> tokenizer = PTBTokenizer.newPTBTokenizer(new BufferedReader(new StringReader(str)));
while (tokenizer.hasNext()) {
Word nextToken = tokenizer.next();
tokens.add(nextToken.toString());
}
if(DEBUG) {
System.out.println("tokens:" + tokens);
}
}
代码示例来源:origin: edu.stanford.nlp/stanford-parser
docStr.append(' ');
docStr.append(aDoc.toString());
内容来源于网络,如有侵权,请联系作者删除!