edu.stanford.nlp.wordseg.CorpusChar Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of stanford-corenlp Show documentation
Show all versions of stanford-corenlp Show documentation
Stanford CoreNLP provides a set of natural language analysis tools which can take raw English language text input and give the base forms of words, their parts of speech, whether they are names of companies, people, etc., normalize dates, times, and numeric quantities, mark up the structure of sentences in terms of phrases and word dependencies, and indicate which noun phrases refer to the same entities. It provides the foundational building blocks for higher level text understanding applications.
package edu.stanford.nlp.wordseg;
import java.util.*;
import java.io.*;
import edu.stanford.nlp.io.IOUtils;
import edu.stanford.nlp.io.RuntimeIOException;
import edu.stanford.nlp.util.Generics;
import edu.stanford.nlp.util.logging.Redwood;
/**
* Check tag of each character from 5 different corpora. (4 official training corpora of Sighan bakeoff 2005, plus CTB)
* These tags are not external knowledge. They are learned from the training corpora.
* @author Huihsin Tseng
* @author Pichuan Chang
*/
public class CorpusChar {
private static final Redwood.RedwoodChannels logger = Redwood.channels(CorpusChar.class);
private Map > charMap;
public CorpusChar(String charlistFilename) {
charMap=readDict(charlistFilename);
}
private Map> getCharMap() {
return charMap;
}
private static Map> readDict(String filename) {
Map> char_dict;
try {
BufferedReader detectorReader = IOUtils.readerFromString(filename, "UTF-8");
char_dict = Generics.newHashMap();
//logger.debug("DEBUG: in CorpusChar readDict");
for (String detectorLine; (detectorLine = detectorReader.readLine()) != null; ) {
String[] fields = detectorLine.split(" ");
String tag=fields[0];
Set chars= char_dict.get(tag);
if(chars==null){
chars = Generics.newHashSet();
char_dict.put(tag,chars);
}
//logger.debug("DEBUG: CorpusChar: "+filename+" "+fields[1]);
chars.add(fields[1]);
}
detectorReader.close();
} catch (IOException e) {
throw new RuntimeIOException(e);
}
logger.info("Loading character dictionary file from " + filename + " [done].");
return char_dict;
}
public String getTag(String a1, String a2) {
Map> h1=getCharMap();
Set h2=h1.get(a1);
if (h2 == null) return "0";
if (h2.contains(a2))
return "1";
return "0";
}
/*
public String getCtbTag(String a1, String a2) {
HashMap h1=dict.getctb();
Set h2=(Set)h1.get(a1);
if (h2 == null) return "0";
if (h2.contains(a2))
return "1";
return "0";
}
public String getAsbcTag(String a1, String a2) {
HashMap h1=dict.getasbc();
Set h2=(Set)h1.get(a1);
if (h2 == null) return "0";
if (h2.contains(a2))
return "1";
return "0";
}
public String getPkuTag(String a1, String a2) {
HashMap h1=dict.getpku();
Set h2=(Set)h1.get(a1);
if (h2 == null) return "0";
if (h2.contains(a2))
return "1";
return "0";
}
public String getHkTag(String a1, String a2) {
HashMap h1=dict.gethk();
Set h2=(Set)h1.get(a1);
if (h2 == null) return "0";
if (h2.contains(a2))
return "1";
return "0";
}
public String getMsrTag(String a1, String a2) {
HashMap h1=dict.getmsr();
Set h2=(Set)h1.get(a1);
if (h2 == null) return "0";
if (h2.contains(a2))
return "1";
return "0";
}*/
}//end of class