use of edu.stanford.nlp.trees.SynchronizedTreeTransformer in project CoreNLP by stanfordnlp.
the class CacheParseHypotheses method main.
/**
* An example of a command line is
* <br>
* java -mx1g edu.stanford.nlp.parser.dvparser.CacheParseHypotheses -model /scr/horatio/dvparser/wsjPCFG.nocompact.simple.ser.gz -output cached9.simple.ser.gz -treebank /afs/ir/data/linguistic-data/Treebank/3/parsed/mrg/wsj 200-202
* <br>
* java -mx4g edu.stanford.nlp.parser.dvparser.CacheParseHypotheses -model ~/scr/dvparser/wsjPCFG.nocompact.simple.ser.gz -output cached.train.simple.ser.gz -treebank /afs/ir/data/linguistic-data/Treebank/3/parsed/mrg/wsj 200-2199 -numThreads 6
* <br>
* java -mx4g edu.stanford.nlp.parser.dvparser.CacheParseHypotheses -model ~/scr/dvparser/chinese/xinhuaPCFG.ser.gz -output cached.xinhua.train.ser.gz -treebank /afs/ir/data/linguistic-data/Chinese-Treebank/6/data/utf8/bracketed 026-270,301-499,600-999
*/
public static void main(String[] args) throws IOException {
String parserModel = null;
String output = null;
List<Pair<String, FileFilter>> treebanks = Generics.newArrayList();
int dvKBest = 200;
int numThreads = 1;
for (int argIndex = 0; argIndex < args.length; ) {
if (args[argIndex].equalsIgnoreCase("-dvKBest")) {
dvKBest = Integer.valueOf(args[argIndex + 1]);
argIndex += 2;
continue;
}
if (args[argIndex].equalsIgnoreCase("-parser") || args[argIndex].equals("-model")) {
parserModel = args[argIndex + 1];
argIndex += 2;
continue;
}
if (args[argIndex].equalsIgnoreCase("-output")) {
output = args[argIndex + 1];
argIndex += 2;
continue;
}
if (args[argIndex].equalsIgnoreCase("-treebank")) {
Pair<String, FileFilter> treebankDescription = ArgUtils.getTreebankDescription(args, argIndex, "-treebank");
argIndex = argIndex + ArgUtils.numSubArgs(args, argIndex) + 1;
treebanks.add(treebankDescription);
continue;
}
if (args[argIndex].equalsIgnoreCase("-numThreads")) {
numThreads = Integer.valueOf(args[argIndex + 1]);
argIndex += 2;
continue;
}
throw new IllegalArgumentException("Unknown argument " + args[argIndex]);
}
if (parserModel == null) {
throw new IllegalArgumentException("Need to supply a parser model with -model");
}
if (output == null) {
throw new IllegalArgumentException("Need to supply an output filename with -output");
}
if (treebanks.size() == 0) {
throw new IllegalArgumentException("Need to supply a treebank with -treebank");
}
log.info("Writing output to " + output);
log.info("Loading parser model " + parserModel);
log.info("Writing " + dvKBest + " hypothesis trees for each tree");
LexicalizedParser parser = LexicalizedParser.loadModel(parserModel, "-dvKBest", Integer.toString(dvKBest));
CacheParseHypotheses cacher = new CacheParseHypotheses(parser);
TreeTransformer transformer = DVParser.buildTrainTransformer(parser.getOp());
List<Tree> sentences = new ArrayList<>();
for (Pair<String, FileFilter> description : treebanks) {
log.info("Reading trees from " + description.first);
Treebank treebank = parser.getOp().tlpParams.memoryTreebank();
treebank.loadPath(description.first, description.second);
treebank = treebank.transform(transformer);
sentences.addAll(treebank);
}
log.info("Processing " + sentences.size() + " trees");
List<Pair<Tree, byte[]>> cache = Generics.newArrayList();
transformer = new SynchronizedTreeTransformer(transformer);
MulticoreWrapper<Tree, Pair<Tree, byte[]>> wrapper = new MulticoreWrapper<>(numThreads, new CacheProcessor(cacher, parser, dvKBest, transformer));
for (Tree tree : sentences) {
wrapper.put(tree);
while (wrapper.peek()) {
cache.add(wrapper.poll());
if (cache.size() % 10 == 0) {
System.out.println("Processed " + cache.size() + " trees");
}
}
}
wrapper.join();
while (wrapper.peek()) {
cache.add(wrapper.poll());
if (cache.size() % 10 == 0) {
System.out.println("Processed " + cache.size() + " trees");
}
}
System.out.println("Finished processing " + cache.size() + " trees");
IOUtils.writeObjectToFile(cache, output);
}
Aggregations