【发布时间】:2015-03-10 19:41:45
【问题描述】:
我正在研究 NLP,我将使用斯坦福解析器从文本中提取名词短语,我使用的解析器版本是 3.4.1 这是我使用的示例代码
package stanfordparser;
import java.util.Collection;
import java.util.List;
import java.io.StringReader;
import edu.stanford.nlp.process.Tokenizer;
import edu.stanford.nlp.process.TokenizerFactory;
import edu.stanford.nlp.process.CoreLabelTokenFactory;
import edu.stanford.nlp.process.DocumentPreprocessor;
import edu.stanford.nlp.process.PTBTokenizer;
import edu.stanford.nlp.ling.CoreLabel;
import edu.stanford.nlp.ling.HasWord;
import edu.stanford.nlp.ling.Sentence;
import edu.stanford.nlp.trees.*;
import edu.stanford.nlp.parser.lexparser.LexicalizedParser;
class ParserDemo {
public static void main(String[] args) {
LexicalizedParser lp = LexicalizedParser.loadModel("edu/stanford/nlp/models/lexparser/englishPCFG.ser.gz");
if (args.length > 0) {
demoDP(lp, args[0]);
} else {
demoAPI(lp);
}
}
public static void demoDP(LexicalizedParser lp, String filename) {
TreebankLanguagePack tlp = new PennTreebankLanguagePack();
GrammaticalStructureFactory gsf = tlp.grammaticalStructureFactory();
for (List<HasWord> sentence : new DocumentPreprocessor(filename)) {
Tree parse = lp.apply(sentence);
parse.pennPrint();
System.out.println();
GrammaticalStructure gs = gsf.newGrammaticalStructure(parse);
Collection tdl = gs.typedDependenciesCCprocessed();
System.out.println(tdl);
System.out.println();
}
}
public static void demoAPI(LexicalizedParser lp) {
// This option shows parsing a list of correctly tokenized words
String[] sent = { "This", "is", "an", "easy", "sentence", "." };
List<CoreLabel> rawWords = Sentence.toCoreLabelList(sent);
Tree parse = lp.apply(rawWords);
parse.pennPrint();
System.out.println();
// This option shows loading and using an explicit tokenizer
String sent2 = "This is another sentence.";
TokenizerFactory<CoreLabel> tokenizerFactory =
PTBTokenizer.factory(new CoreLabelTokenFactory(), "");
Tokenizer<CoreLabel> tok =
tokenizerFactory.getTokenizer(new StringReader(sent2));
List<CoreLabel> rawWords2 = tok.tokenize();
parse = lp.apply(rawWords2);
TreebankLanguagePack tlp = new PennTreebankLanguagePack();
GrammaticalStructureFactory gsf = tlp.grammaticalStructureFactory();
GrammaticalStructure gs = gsf.newGrammaticalStructure(parse);
List<TypedDependency> tdl = gs.typedDependenciesCCprocessed();
System.out.println(tdl);
System.out.println();
// You can also use a TreePrint object to print trees and dependencies
TreePrint tp = new TreePrint("penn,typedDependenciesCollapsed");
tp.printTree(parse);
}
private ParserDemo() {} // static methods only
}
但是当我运行这段代码时,我得到了以下错误
java.io.IOException: Unable to resolve "edu/stanford/nlp/models/lexparser/englishPCFG.ser.gz" as either class path, filename or URL
at edu.stanford.nlp.io.IOUtils.getInputStreamFromURLOrClasspathOrFileSystem(IOUtils.java:446)
at edu.stanford.nlp.io.IOUtils.readStreamFromString(IOUtils.java:380)
at edu.stanford.nlp.parser.lexparser.LexicalizedParser.getParserFromSerializedFile(LexicalizedParser.java:628)
at edu.stanford.nlp.parser.lexparser.LexicalizedParser.getParserFromFile(LexicalizedParser.java:423)
at edu.stanford.nlp.parser.lexparser.LexicalizedParser.loadModel(LexicalizedParser.java:182)
at edu.stanford.nlp.parser.lexparser.LexicalizedParser.loadModel(LexicalizedParser.java:161)
at stanfordparser.ParserDemo.main(ParserDemo.java:29)
我认为是加载模型文件的问题, 任何人都可以帮我解决这个问题吗? 谢谢
更新:(1) 我已经包含了cornlp 模型罐
更新:(2)我正在使用 Netbeans
【问题讨论】:
标签: java parsing nlp stanford-nlp