public class Util extends Object
Modifier and Type | Method and Description |
---|---|
static List<String> |
generateDict(List<String> str) |
static List<String> |
generateDict(List<String> str,
int cutOff)
Build a dictionary of words collected from a corpus.
|
static <T> List<T> |
getRandomSubList(List<T> input,
int subsetSize) |
static void |
loadConllFile(String inFile,
List<CoreMap> sents,
List<edu.stanford.nlp.parser.nndep.DependencyTree> trees) |
static void |
loadConllFile(String inFile,
List<CoreMap> sents,
List<edu.stanford.nlp.parser.nndep.DependencyTree> trees,
boolean unlabeled,
boolean cPOS) |
static void |
printTreeStats(List<edu.stanford.nlp.parser.nndep.DependencyTree> trees) |
static void |
printTreeStats(String str,
List<edu.stanford.nlp.parser.nndep.DependencyTree> trees) |
static double[][] |
scaling(double[][] A)
Normalize word embeddings by setting mean = 0, std = 1
|
static double[][] |
scaling(double[][] A,
double rMean,
double rStd)
Normalize word embeddings by setting mean = rMean, std = rStd
|
static void |
writeConllFile(String outFile,
List<CoreMap> sentences,
List<edu.stanford.nlp.parser.nndep.DependencyTree> trees) |
public static double[][] scaling(double[][] A, double rMean, double rStd)
public static double[][] scaling(double[][] A)
public static List<String> generateDict(List<String> str, int cutOff)
Filters out words with a frequency below the given cutOff
.
cutOff
public static void loadConllFile(String inFile, List<CoreMap> sents, List<edu.stanford.nlp.parser.nndep.DependencyTree> trees, boolean unlabeled, boolean cPOS)
public static void loadConllFile(String inFile, List<CoreMap> sents, List<edu.stanford.nlp.parser.nndep.DependencyTree> trees)
public static void writeConllFile(String outFile, List<CoreMap> sentences, List<edu.stanford.nlp.parser.nndep.DependencyTree> trees)
public static void printTreeStats(String str, List<edu.stanford.nlp.parser.nndep.DependencyTree> trees)
public static void printTreeStats(List<edu.stanford.nlp.parser.nndep.DependencyTree> trees)