List of usage examples for edu.stanford.nlp.ie AbstractSequenceClassifier classifyToCharacterOffsets
public List<Triple<String, Integer, Integer>> classifyToCharacterOffsets(String sentences)
From source file:com.bericotech.clavin.nerd.WorkflowDemoNERD.java
License:Open Source License
/** * Sometimes, you might already be using Stanford NER elsewhere in * your application, and you'd like to just pass the output from * Stanford NER directly into CLAVIN, without having to re-run the * input through Stanford NER just to use CLAVIN. This example * shows you how to very easily do exactly that. * * @throws IOException//from ww w . j ava2 s . c o m * @throws ClavinException */ private static void resolveStanfordEntities() throws IOException, ClavinException { /*##################################################################### * * Start with Stanford NER -- no need to get CLAVIN involved for now. * *###################################################################*/ // instantiate Stanford NER entity extractor InputStream mpis = WorkflowDemoNERD.class.getClassLoader() .getResourceAsStream("models/english.all.3class.distsim.prop"); Properties mp = new Properties(); mp.load(mpis); AbstractSequenceClassifier<CoreMap> namedEntityRecognizer = CRFClassifier .getJarClassifier("/models/english.all.3class.distsim.crf.ser.gz", mp); // Unstructured text file about Somalia to be geoparsed File inputFile = new File("src/test/resources/sample-docs/Somalia-doc.txt"); // Grab the contents of the text file as a String String inputString = TextUtils.fileToString(inputFile); // extract entities from input text using Stanford NER List<Triple<String, Integer, Integer>> entitiesFromNER = namedEntityRecognizer .classifyToCharacterOffsets(inputString); /*##################################################################### * * Now, CLAVIN comes into play... * *###################################################################*/ // convert Stanford NER output to ClavinLocationResolver input List<LocationOccurrence> locationsForCLAVIN = convertNERtoCLAVIN(entitiesFromNER, inputString); // instantiate the CLAVIN location resolver ClavinLocationResolver clavinLocationResolver = new ClavinLocationResolver( new LuceneGazetteer(new File("./IndexDirectory"))); // resolve location entities extracted from input text List<ResolvedLocation> resolvedLocations = clavinLocationResolver.resolveLocations(locationsForCLAVIN, 1, 1, false); // Display the ResolvedLocations found for the location names for (ResolvedLocation resolvedLocation : resolvedLocations) System.out.println(resolvedLocation); }
From source file:fire.NERDemo.java
public static void main(String[] args) throws Exception { String serializedClassifier = "C:\\Users\\DIPANAKR\\Desktop\\Satanu\\fire\\stanford-ner-2015-04-20\\stanford-ner-2015-04-20\\classifiers\\english.all.3class.distsim.crf.ser.gz"; if (args.length > 0) { serializedClassifier = args[0];//from ww w. j a va 2 s . co m } AbstractSequenceClassifier<CoreLabel> classifier = CRFClassifier.getClassifier(serializedClassifier); /* For either a file to annotate or for the hardcoded text example, this demo file shows several ways to process the input, for teaching purposes. */ if (args.length > 1) { /* For the file, it shows (1) how to run NER on a String, (2) how to get the entities in the String with character offsets, and (3) how to run NER on a whole file (without loading it into a String). */ String fileContents = IOUtils.slurpFile(args[1]); List<List<CoreLabel>> out = classifier.classify(fileContents); for (List<CoreLabel> sentence : out) { for (CoreLabel word : sentence) { System.out.print(word.word() + '/' + word.get(CoreAnnotations.AnswerAnnotation.class) + ' '); } System.out.println(); } System.out.println("---"); out = classifier.classifyFile(args[1]); for (List<CoreLabel> sentence : out) { for (CoreLabel word : sentence) { System.out.print(word.word() + '/' + word.get(CoreAnnotations.AnswerAnnotation.class) + ' '); } System.out.println(); } System.out.println("---"); List<Triple<String, Integer, Integer>> list = classifier.classifyToCharacterOffsets(fileContents); for (Triple<String, Integer, Integer> item : list) { System.out.println(item.first() + ": " + fileContents.substring(item.second(), item.third())); } System.out.println("---"); System.out.println("Ten best entity labelings"); DocumentReaderAndWriter<CoreLabel> readerAndWriter = classifier.makePlainTextReaderAndWriter(); classifier.classifyAndWriteAnswersKBest(args[1], 10, readerAndWriter); System.out.println("---"); System.out.println("Per-token marginalized probabilities"); classifier.printProbs(args[1], readerAndWriter); // -- This code prints out the first order (token pair) clique probabilities. // -- But that output is a bit overwhelming, so we leave it commented out by default. // System.out.println("---"); // System.out.println("First Order Clique Probabilities"); // ((CRFClassifier) classifier).printFirstOrderProbs(args[1], readerAndWriter); } else { /* For the hard-coded String, it shows how to run it on a single sentence, and how to do this and produce several formats, including slash tags and an inline XML output format. It also shows the full contents of the {@code CoreLabel}s that are constructed by the classifier. And it shows getting out the probabilities of different assignments and an n-best list of classifications with probabilities. */ String[] example = { "Good afternoon Rajat Raina, how are you today?", "I go to school at Stanford University, which is located in California." }; for (String str : example) { System.out.println(classifier.classifyToString(str)); } System.out.println("---"); for (String str : example) { // This one puts in spaces and newlines between tokens, so just print not println. System.out.print(classifier.classifyToString(str, "slashTags", false)); } System.out.println("---"); for (String str : example) { // This one is best for dealing with the output as a TSV (tab-separated column) file. // The first column gives entities, the second their classes, and the third the remaining text in a document System.out.print(classifier.classifyToString(str, "tabbedEntities", false)); } System.out.println("---"); for (String str : example) { System.out.println(classifier.classifyWithInlineXML(str)); } System.out.println("---"); for (String str : example) { System.out.println(classifier.classifyToString(str, "xml", true)); } System.out.println("---"); for (String str : example) { System.out.print(classifier.classifyToString(str, "tsv", false)); } System.out.println("---"); // This gets out entities with character offsets int j = 0; for (String str : example) { j++; List<Triple<String, Integer, Integer>> triples = classifier.classifyToCharacterOffsets(str); for (Triple<String, Integer, Integer> trip : triples) { System.out.printf("%s over character offsets [%d, %d) in sentence %d.%n", trip.first(), trip.second(), trip.third, j); } } System.out.println("---"); // This prints out all the details of what is stored for each token int i = 0; for (String str : example) { for (List<CoreLabel> lcl : classifier.classify(str)) { for (CoreLabel cl : lcl) { System.out.print(i++ + ": "); System.out.println(cl.toShorterString()); } } } System.out.println("---"); } }