private static Edu.Stanford.Nlp.Parser.Lexparser.ChineseLexiconAndWordSegmenter GetSegmenterDataFromTreebank(Treebank trainTreebank, Options op, IIndex <string> wordIndex, IIndex <string> tagIndex)
{
System.Console.Out.WriteLine("Currently " + new DateTime());
// printOptions(true, op);
Timing.StartTime();
// setup tree transforms
ITreebankLangParserParams tlpParams = op.tlpParams;
if (op.testOptions.verbose)
{
System.Console.Out.Write("Training ");
System.Console.Out.WriteLine(trainTreebank.TextualSummary());
}
System.Console.Out.Write("Binarizing trees...");
TreeAnnotatorAndBinarizer binarizer;
// initialized below
if (!op.trainOptions.leftToRight)
{
binarizer = new TreeAnnotatorAndBinarizer(tlpParams, op.forceCNF, !op.trainOptions.OutsideFactor(), true, op);
}
else
{
binarizer = new TreeAnnotatorAndBinarizer(tlpParams.HeadFinder(), new LeftHeadFinder(), tlpParams, op.forceCNF, !op.trainOptions.OutsideFactor(), true, op);
}
CollinsPuncTransformer collinsPuncTransformer = null;
if (op.trainOptions.collinsPunc)
{
collinsPuncTransformer = new CollinsPuncTransformer(tlpParams.TreebankLanguagePack());
}
IList <Tree> binaryTrainTrees = new List <Tree>();
// List<Tree> binaryTuneTrees = new ArrayList<Tree>();
if (op.trainOptions.selectiveSplit)
{
op.trainOptions.splitters = ParentAnnotationStats.GetSplitCategories(trainTreebank, true, 0, op.trainOptions.selectiveSplitCutOff, op.trainOptions.tagSelectiveSplitCutOff, tlpParams.TreebankLanguagePack());
if (op.testOptions.verbose)
{
log.Info("Parent split categories: " + op.trainOptions.splitters);
}
}
if (op.trainOptions.selectivePostSplit)
{
ITreeTransformer myTransformer = new TreeAnnotator(tlpParams.HeadFinder(), tlpParams, op);
Treebank annotatedTB = trainTreebank.Transform(myTransformer);
op.trainOptions.postSplitters = ParentAnnotationStats.GetSplitCategories(annotatedTB, true, 0, op.trainOptions.selectivePostSplitCutOff, op.trainOptions.tagSelectivePostSplitCutOff, tlpParams.TreebankLanguagePack());
if (op.testOptions.verbose)
{
log.Info("Parent post annotation split categories: " + op.trainOptions.postSplitters);
}
}
if (op.trainOptions.hSelSplit)
{
binarizer.SetDoSelectiveSplit(false);
foreach (Tree tree in trainTreebank)
{
if (op.trainOptions.collinsPunc)
{
tree = collinsPuncTransformer.TransformTree(tree);
}
tree = binarizer.TransformTree(tree);
}
binarizer.SetDoSelectiveSplit(true);
}
foreach (Tree tree_1 in trainTreebank)
{
if (op.trainOptions.collinsPunc)
{
tree_1 = collinsPuncTransformer.TransformTree(tree_1);
}
tree_1 = binarizer.TransformTree(tree_1);
binaryTrainTrees.Add(tree_1);
}
Timing.Tick("done.");
if (op.testOptions.verbose)
{
binarizer.DumpStats();
}
System.Console.Out.Write("Extracting Lexicon...");
Edu.Stanford.Nlp.Parser.Lexparser.ChineseLexiconAndWordSegmenter clex = (Edu.Stanford.Nlp.Parser.Lexparser.ChineseLexiconAndWordSegmenter)op.tlpParams.Lex(op, wordIndex, tagIndex);
clex.InitializeTraining(binaryTrainTrees.Count);
clex.Train(binaryTrainTrees);
clex.FinishTraining();
Timing.Tick("done.");
return(clex);
}
/// <summary>Run the scoring metric on guess/gold input.</summary>
/// <remarks>
/// Run the scoring metric on guess/gold input. This method performs "Collinization."
/// The default language is English.
/// </remarks>
/// <param name="args"/>
public static void Main(string[] args)
{
if (args.Length < minArgs)
{
System.Console.Out.WriteLine(usage.ToString());
System.Environment.Exit(-1);
}
ITreebankLangParserParams tlpp = new EnglishTreebankParserParams();
int maxGoldYield = int.MaxValue;
bool Verbose = false;
string encoding = "UTF-8";
string guessFile = null;
string goldFile = null;
IDictionary <string, string[]> argsMap = StringUtils.ArgsToMap(args, optionArgDefs);
foreach (KeyValuePair <string, string[]> opt in argsMap)
{
if (opt.Key == null)
{
continue;
}
if (opt.Key.Equals("-l"))
{
Language lang = Language.ValueOf(opt.Value[0].Trim());
tlpp = lang.@params;
}
else
{
if (opt.Key.Equals("-y"))
{
maxGoldYield = System.Convert.ToInt32(opt.Value[0].Trim());
}
else
{
if (opt.Key.Equals("-v"))
{
Verbose = true;
}
else
{
if (opt.Key.Equals("-c"))
{
Edu.Stanford.Nlp.Parser.Metrics.TaggingEval.doCatLevelEval = true;
}
else
{
if (opt.Key.Equals("-e"))
{
encoding = opt.Value[0];
}
else
{
log.Info(usage.ToString());
System.Environment.Exit(-1);
}
}
}
}
}
//Non-option arguments located at key null
string[] rest = argsMap[null];
if (rest == null || rest.Length < minArgs)
{
log.Info(usage.ToString());
System.Environment.Exit(-1);
}
goldFile = rest[0];
guessFile = rest[1];
}
tlpp.SetInputEncoding(encoding);
PrintWriter pwOut = tlpp.Pw();
Treebank guessTreebank = tlpp.DiskTreebank();
guessTreebank.LoadPath(guessFile);
pwOut.Println("GUESS TREEBANK:");
pwOut.Println(guessTreebank.TextualSummary());
Treebank goldTreebank = tlpp.DiskTreebank();
goldTreebank.LoadPath(goldFile);
pwOut.Println("GOLD TREEBANK:");
pwOut.Println(goldTreebank.TextualSummary());
Edu.Stanford.Nlp.Parser.Metrics.TaggingEval metric = new Edu.Stanford.Nlp.Parser.Metrics.TaggingEval("Tagging LP/LR");
ITreeTransformer tc = tlpp.Collinizer();
//The evalb ref implementation assigns status for each tree pair as follows:
//
// 0 - Ok (yields match)
// 1 - length mismatch
// 2 - null parse e.g. (()).
//
//In the cases of 1,2, evalb does not include the tree pair in the LP/LR computation.
IEnumerator <Tree> goldItr = goldTreebank.GetEnumerator();
IEnumerator <Tree> guessItr = guessTreebank.GetEnumerator();
int goldLineId = 0;
int guessLineId = 0;
int skippedGuessTrees = 0;
while (guessItr.MoveNext() && goldItr.MoveNext())
{
Tree guessTree = guessItr.Current;
IList <ILabel> guessYield = guessTree.Yield();
guessLineId++;
Tree goldTree = goldItr.Current;
IList <ILabel> goldYield = goldTree.Yield();
goldLineId++;
// Check that we should evaluate this tree
if (goldYield.Count > maxGoldYield)
{
skippedGuessTrees++;
continue;
}
// Only trees with equal yields can be evaluated
if (goldYield.Count != guessYield.Count)
{
pwOut.Printf("Yield mismatch gold: %d tokens vs. guess: %d tokens (lines: gold %d guess %d)%n", goldYield.Count, guessYield.Count, goldLineId, guessLineId);
skippedGuessTrees++;
continue;
}
Tree evalGuess = tc.TransformTree(guessTree);
Tree evalGold = tc.TransformTree(goldTree);
metric.Evaluate(evalGuess, evalGold, ((Verbose) ? pwOut : null));
}
if (guessItr.MoveNext() || goldItr.MoveNext())
{
System.Console.Error.Printf("Guess/gold files do not have equal lengths (guess: %d gold: %d)%n.", guessLineId, goldLineId);
}
pwOut.Println("================================================================================");
if (skippedGuessTrees != 0)
{
pwOut.Printf("%s %d guess trees\n", "Unable to evaluate", skippedGuessTrees);
}
metric.Display(true, pwOut);
pwOut.Println();
pwOut.Close();
}
/// <returns>A Triple of binaryTrainTreebank, binarySecondaryTreebank, binaryTuneTreebank.</returns>
public static Triple <Treebank, Treebank, Treebank> GetAnnotatedBinaryTreebankFromTreebank(Treebank trainTreebank, Treebank secondaryTreebank, Treebank tuneTreebank, Options op)
{
// setup tree transforms
ITreebankLangParserParams tlpParams = op.tlpParams;
ITreebankLanguagePack tlp = tlpParams.TreebankLanguagePack();
if (op.testOptions.verbose)
{
PrintWriter pwErr = tlpParams.Pw(System.Console.Error);
pwErr.Print("Training ");
pwErr.Println(trainTreebank.TextualSummary(tlp));
if (secondaryTreebank != null)
{
pwErr.Print("Secondary training ");
pwErr.Println(secondaryTreebank.TextualSummary(tlp));
}
}
CompositeTreeTransformer trainTransformer = new CompositeTreeTransformer();
if (op.trainOptions.preTransformer != null)
{
trainTransformer.AddTransformer(op.trainOptions.preTransformer);
}
if (op.trainOptions.collinsPunc)
{
CollinsPuncTransformer collinsPuncTransformer = new CollinsPuncTransformer(tlp);
trainTransformer.AddTransformer(collinsPuncTransformer);
}
log.Info("Binarizing trees...");
Edu.Stanford.Nlp.Parser.Lexparser.TreeAnnotatorAndBinarizer binarizer;
if (!op.trainOptions.leftToRight)
{
binarizer = new Edu.Stanford.Nlp.Parser.Lexparser.TreeAnnotatorAndBinarizer(tlpParams, op.forceCNF, !op.trainOptions.OutsideFactor(), !op.trainOptions.predictSplits, op);
}
else
{
binarizer = new Edu.Stanford.Nlp.Parser.Lexparser.TreeAnnotatorAndBinarizer(tlpParams.HeadFinder(), new LeftHeadFinder(), tlpParams, op.forceCNF, !op.trainOptions.OutsideFactor(), !op.trainOptions.predictSplits, op);
}
trainTransformer.AddTransformer(binarizer);
if (op.wordFunction != null)
{
ITreeTransformer wordFunctionTransformer = new TreeLeafLabelTransformer(op.wordFunction);
trainTransformer.AddTransformer(wordFunctionTransformer);
}
Treebank wholeTreebank;
if (secondaryTreebank == null)
{
wholeTreebank = trainTreebank;
}
else
{
wholeTreebank = new CompositeTreebank(trainTreebank, secondaryTreebank);
}
if (op.trainOptions.selectiveSplit)
{
op.trainOptions.splitters = ParentAnnotationStats.GetSplitCategories(wholeTreebank, op.trainOptions.tagSelectiveSplit, 0, op.trainOptions.selectiveSplitCutOff, op.trainOptions.tagSelectiveSplitCutOff, tlp);
RemoveDeleteSplittersFromSplitters(tlp, op);
if (op.testOptions.verbose)
{
IList <string> list = new List <string>(op.trainOptions.splitters);
list.Sort();
log.Info("Parent split categories: " + list);
}
}
if (op.trainOptions.selectivePostSplit)
{
// Do all the transformations once just to learn selective splits on annotated categories
ITreeTransformer myTransformer = new TreeAnnotator(tlpParams.HeadFinder(), tlpParams, op);
wholeTreebank = wholeTreebank.Transform(myTransformer);
op.trainOptions.postSplitters = ParentAnnotationStats.GetSplitCategories(wholeTreebank, true, 0, op.trainOptions.selectivePostSplitCutOff, op.trainOptions.tagSelectivePostSplitCutOff, tlp);
if (op.testOptions.verbose)
{
log.Info("Parent post annotation split categories: " + op.trainOptions.postSplitters);
}
}
if (op.trainOptions.hSelSplit)
{
// We run through all the trees once just to gather counts for hSelSplit!
int ptt = op.trainOptions.printTreeTransformations;
op.trainOptions.printTreeTransformations = 0;
binarizer.SetDoSelectiveSplit(false);
foreach (Tree tree in wholeTreebank)
{
trainTransformer.TransformTree(tree);
}
binarizer.SetDoSelectiveSplit(true);
op.trainOptions.printTreeTransformations = ptt;
}
// we've done all the setup now. here's where the train treebank is transformed.
trainTreebank = trainTreebank.Transform(trainTransformer);
if (secondaryTreebank != null)
{
secondaryTreebank = secondaryTreebank.Transform(trainTransformer);
}
if (op.trainOptions.printAnnotatedStateCounts)
{
binarizer.PrintStateCounts();
}
if (op.trainOptions.printAnnotatedRuleCounts)
{
binarizer.PrintRuleCounts();
}
if (tuneTreebank != null)
{
tuneTreebank = tuneTreebank.Transform(trainTransformer);
}
if (op.testOptions.verbose)
{
binarizer.DumpStats();
}
return(new Triple <Treebank, Treebank, Treebank>(trainTreebank, secondaryTreebank, tuneTreebank));
}
/// <summary>Run the Evalb scoring metric on guess/gold input.</summary>
/// <remarks>Run the Evalb scoring metric on guess/gold input. The default language is English.</remarks>
/// <param name="args"/>
public static void Main(string[] args)
{
if (args.Length < minArgs)
{
log.Info(Usage());
System.Environment.Exit(-1);
}
Properties options = StringUtils.ArgsToProperties(args, OptionArgDefs());
Language language = PropertiesUtils.Get(options, "l", Language.English, typeof(Language));
ITreebankLangParserParams tlpp = language.@params;
int maxGoldYield = PropertiesUtils.GetInt(options, "y", int.MaxValue);
bool Verbose = PropertiesUtils.GetBool(options, "v", false);
bool sortByF1 = PropertiesUtils.HasProperty(options, "s");
int worstKTreesToEmit = PropertiesUtils.GetInt(options, "s", 0);
PriorityQueue <Triple <double, Tree, Tree> > queue = sortByF1 ? new PriorityQueue <Triple <double, Tree, Tree> >(2000, new Evalb.F1Comparator()) : null;
bool doCatLevel = PropertiesUtils.GetBool(options, "c", false);
string labelRegex = options.GetProperty("f", null);
string encoding = options.GetProperty("e", "UTF-8");
string[] parsedArgs = options.GetProperty(string.Empty, string.Empty).Split("\\s+");
if (parsedArgs.Length != minArgs)
{
log.Info(Usage());
System.Environment.Exit(-1);
}
string goldFile = parsedArgs[0];
string guessFile = parsedArgs[1];
// Command-line has been parsed. Configure the metric for evaluation.
tlpp.SetInputEncoding(encoding);
PrintWriter pwOut = tlpp.Pw();
Treebank guessTreebank = tlpp.DiskTreebank();
guessTreebank.LoadPath(guessFile);
pwOut.Println("GUESS TREEBANK:");
pwOut.Println(guessTreebank.TextualSummary());
Treebank goldTreebank = tlpp.DiskTreebank();
goldTreebank.LoadPath(goldFile);
pwOut.Println("GOLD TREEBANK:");
pwOut.Println(goldTreebank.TextualSummary());
Evalb metric = new Evalb("Evalb LP/LR", true);
EvalbByCat evalbCat = (doCatLevel) ? new EvalbByCat("EvalbByCat LP/LR", true, labelRegex) : null;
ITreeTransformer tc = tlpp.Collinizer();
//The evalb ref implementation assigns status for each tree pair as follows:
//
// 0 - Ok (yields match)
// 1 - length mismatch
// 2 - null parse e.g. (()).
//
//In the cases of 1,2, evalb does not include the tree pair in the LP/LR computation.
IEnumerator <Tree> goldItr = goldTreebank.GetEnumerator();
IEnumerator <Tree> guessItr = guessTreebank.GetEnumerator();
int goldLineId = 0;
int guessLineId = 0;
int skippedGuessTrees = 0;
while (guessItr.MoveNext() && goldItr.MoveNext())
{
Tree guessTree = guessItr.Current;
IList <ILabel> guessYield = guessTree.Yield();
guessLineId++;
Tree goldTree = goldItr.Current;
IList <ILabel> goldYield = goldTree.Yield();
goldLineId++;
// Check that we should evaluate this tree
if (goldYield.Count > maxGoldYield)
{
skippedGuessTrees++;
continue;
}
// Only trees with equal yields can be evaluated
if (goldYield.Count != guessYield.Count)
{
pwOut.Printf("Yield mismatch gold: %d tokens vs. guess: %d tokens (lines: gold %d guess %d)%n", goldYield.Count, guessYield.Count, goldLineId, guessLineId);
skippedGuessTrees++;
continue;
}
Tree evalGuess = tc.TransformTree(guessTree);
Tree evalGold = tc.TransformTree(goldTree);
metric.Evaluate(evalGuess, evalGold, ((Verbose) ? pwOut : null));
if (doCatLevel)
{
evalbCat.Evaluate(evalGuess, evalGold, ((Verbose) ? pwOut : null));
}
if (sortByF1)
{
StoreTrees(queue, guessTree, goldTree, metric.GetLastF1());
}
}
if (guessItr.MoveNext() || goldItr.MoveNext())
{
System.Console.Error.Printf("Guess/gold files do not have equal lengths (guess: %d gold: %d)%n.", guessLineId, goldLineId);
}
pwOut.Println("================================================================================");
if (skippedGuessTrees != 0)
{
pwOut.Printf("%s %d guess trees\n", "Unable to evaluate", skippedGuessTrees);
}
metric.Display(true, pwOut);
pwOut.Println();
if (doCatLevel)
{
evalbCat.Display(true, pwOut);
pwOut.Println();
}
if (sortByF1)
{
EmitSortedTrees(queue, worstKTreesToEmit, guessFile);
}
pwOut.Close();
}
public virtual IList <Tree> GetAnnotatedBinaryTreebankFromTreebank(Treebank trainTreebank)
{
ITreebankLangParserParams tlpParams = op.tlpParams;
ITreebankLanguagePack tlp = tlpParams.TreebankLanguagePack();
if (Verbose)
{
log.Info("\n\n" + trainTreebank.TextualSummary(tlp));
}
log.Info("Binarizing trees...");
TreeAnnotatorAndBinarizer binarizer = new TreeAnnotatorAndBinarizer(tlpParams, op.forceCNF, !op.trainOptions.OutsideFactor(), true, op);
Timing.Tick("done.");
if (op.trainOptions.selectiveSplit)
{
op.trainOptions.splitters = ParentAnnotationStats.GetSplitCategories(trainTreebank, op.trainOptions.tagSelectiveSplit, 0, op.trainOptions.selectiveSplitCutOff, op.trainOptions.tagSelectiveSplitCutOff, tlp);
RemoveDeleteSplittersFromSplitters(tlp);
if (op.testOptions.verbose)
{
IList <string> list = new List <string>(op.trainOptions.splitters);
list.Sort();
log.Info("Parent split categories: " + list);
}
}
// if (op.trainOptions.selectivePostSplit) {
// // Do all the transformations once just to learn selective splits on annotated categories
// TreeTransformer myTransformer = new TreeAnnotator(tlpParams.headFinder(), tlpParams);
// Treebank annotatedTB = trainTreebank.transform(myTransformer);
// op.trainOptions.postSplitters = ParentAnnotationStats.getSplitCategories(annotatedTB, true, 0, op.trainOptions.selectivePostSplitCutOff, op.trainOptions.tagSelectivePostSplitCutOff, tlp);
// if (op.testOptions.verbose) {
// log.info("Parent post annotation split categories: " + op.trainOptions.postSplitters);
// }
// }
if (op.trainOptions.hSelSplit)
{
// We run through all the trees once just to gather counts for hSelSplit!
int ptt = op.trainOptions.printTreeTransformations;
op.trainOptions.printTreeTransformations = 0;
binarizer.SetDoSelectiveSplit(false);
foreach (Tree tree in trainTreebank)
{
binarizer.TransformTree(tree);
}
binarizer.SetDoSelectiveSplit(true);
op.trainOptions.printTreeTransformations = ptt;
}
//Tree transformation
//
IList <Tree> binaryTrainTrees = new List <Tree>();
foreach (Tree tree_1 in trainTreebank)
{
tree_1 = binarizer.TransformTree(tree_1);
if (tree_1.Yield().Count - 1 <= trainLengthLimit)
{
binaryTrainTrees.Add(tree_1);
}
}
// WSGDEBUG: Lot's of stuff on the grammar
// if(VERBOSE) {
// binarizer.printStateCounts();
// binarizer.printRuleCounts();
// binarizer.dumpStats();
// }
return(binaryTrainTrees);
}
/// <summary>Run the scoring metric on guess/gold input.</summary>
/// <remarks>
/// Run the scoring metric on guess/gold input. This method performs "Collinization."
/// The default language is English.
/// </remarks>
/// <param name="args"/>
public static void Main(string[] args)
{
if (args.Length < minArgs)
{
System.Console.Out.WriteLine(usage.ToString());
System.Environment.Exit(-1);
}
ITreebankLangParserParams tlpp = new EnglishTreebankParserParams();
int maxGoldYield = int.MaxValue;
int maxGuessYield = int.MaxValue;
bool Verbose = false;
bool skipGuess = false;
bool tagMode = false;
string guessFile = null;
string goldFile = null;
for (int i = 0; i < args.Length; i++)
{
if (args[i].StartsWith("-"))
{
switch (args[i])
{
case "-l":
{
Language lang = Language.ValueOf(args[++i].Trim());
tlpp = lang.@params;
break;
}
case "-y":
{
maxGoldYield = System.Convert.ToInt32(args[++i].Trim());
break;
}
case "-t":
{
tagMode = true;
break;
}
case "-v":
{
Verbose = true;
break;
}
case "-g":
{
maxGuessYield = System.Convert.ToInt32(args[++i].Trim());
skipGuess = true;
break;
}
default:
{
System.Console.Out.WriteLine(usage.ToString());
System.Environment.Exit(-1);
break;
}
}
}
else
{
//Required parameters
goldFile = args[i++];
guessFile = args[i];
break;
}
}
PrintWriter pwOut = tlpp.Pw();
Treebank guessTreebank = tlpp.DiskTreebank();
guessTreebank.LoadPath(guessFile);
pwOut.Println("GUESS TREEBANK:");
pwOut.Println(guessTreebank.TextualSummary());
Treebank goldTreebank = tlpp.DiskTreebank();
goldTreebank.LoadPath(goldFile);
pwOut.Println("GOLD TREEBANK:");
pwOut.Println(goldTreebank.TextualSummary());
string evalName = (tagMode) ? "TsarfatyTAG" : "TsarfatySEG";
Edu.Stanford.Nlp.Parser.Metrics.TsarfatyEval eval = new Edu.Stanford.Nlp.Parser.Metrics.TsarfatyEval(evalName, tagMode);
ITreeTransformer tc = tlpp.Collinizer();
//PennTreeReader skips over null/malformed parses. So when the yields of the gold/guess trees
//don't match, we need to keep looking for the next gold tree that matches.
//The evalb ref implementation differs slightly as it expects one tree per line. It assigns
//status as follows:
//
// 0 - Ok (yields match)
// 1 - length mismatch
// 2 - null parse e.g. (()).
//
//In the cases of 1,2, evalb does not include the tree pair in the LP/LR computation.
IEnumerator <Tree> goldItr = goldTreebank.GetEnumerator();
int goldLineId = 0;
int skippedGuessTrees = 0;
foreach (Tree guess in guessTreebank)
{
Tree evalGuess = tc.TransformTree(guess);
List <ILabel> guessSent = guess.Yield();
string guessChars = SentenceUtils.ListToString(guessSent).ReplaceAll("\\s+", string.Empty);
if (guessSent.Count > maxGuessYield)
{
skippedGuessTrees++;
continue;
}
bool doneEval = false;
while (goldItr.MoveNext() && !doneEval)
{
Tree gold = goldItr.Current;
Tree evalGold = tc.TransformTree(gold);
goldLineId++;
List <ILabel> goldSent = gold.Yield();
string goldChars = SentenceUtils.ListToString(goldSent).ReplaceAll("\\s+", string.Empty);
if (goldSent.Count > maxGoldYield)
{
continue;
}
else
{
if (goldChars.Length != guessChars.Length)
{
pwOut.Printf("Char level yield mismatch at line %d (guess: %d gold: %d)\n", goldLineId, guessChars.Length, goldChars.Length);
skippedGuessTrees++;
break;
}
}
//Default evalb behavior -- skip this guess tree
eval.Evaluate(evalGuess, evalGold, ((Verbose) ? pwOut : null));
doneEval = true;
}
}
//Move to the next guess parse
pwOut.Println("================================================================================");
if (skippedGuessTrees != 0)
{
pwOut.Printf("%s %d guess trees\n", ((skipGuess) ? "Skipped" : "Unable to evaluate"), skippedGuessTrees);
}
eval.Display(true, pwOut);
pwOut.Println();
pwOut.Close();
}
/// <summary>Execute with no arguments for usage.</summary>
public static void Main(string[] args)
{
if (!ValidateCommandLine(args))
{
log.Info(Usage);
System.Environment.Exit(-1);
}
ITreebankLangParserParams tlpp = Language.@params;
PrintWriter pwOut = tlpp.Pw();
Treebank guessTreebank = tlpp.DiskTreebank();
guessTreebank.LoadPath(guessFile);
pwOut.Println("GUESS TREEBANK:");
pwOut.Println(guessTreebank.TextualSummary());
Treebank goldTreebank = tlpp.DiskTreebank();
goldTreebank.LoadPath(goldFile);
pwOut.Println("GOLD TREEBANK:");
pwOut.Println(goldTreebank.TextualSummary());
Edu.Stanford.Nlp.Parser.Metrics.LeafAncestorEval metric = new Edu.Stanford.Nlp.Parser.Metrics.LeafAncestorEval("LeafAncestor");
ITreeTransformer tc = tlpp.Collinizer();
//The evalb ref implementation assigns status for each tree pair as follows:
//
// 0 - Ok (yields match)
// 1 - length mismatch
// 2 - null parse e.g. (()).
//
//In the cases of 1,2, evalb does not include the tree pair in the LP/LR computation.
IEnumerator <Tree> goldItr = goldTreebank.GetEnumerator();
IEnumerator <Tree> guessItr = guessTreebank.GetEnumerator();
int goldLineId = 0;
int guessLineId = 0;
int skippedGuessTrees = 0;
while (guessItr.MoveNext() && goldItr.MoveNext())
{
Tree guessTree = guessItr.Current;
IList <ILabel> guessYield = guessTree.Yield();
guessLineId++;
Tree goldTree = goldItr.Current;
IList <ILabel> goldYield = goldTree.Yield();
goldLineId++;
// Check that we should evaluate this tree
if (goldYield.Count > MaxGoldYield)
{
skippedGuessTrees++;
continue;
}
// Only trees with equal yields can be evaluated
if (goldYield.Count != guessYield.Count)
{
pwOut.Printf("Yield mismatch gold: %d tokens vs. guess: %d tokens (lines: gold %d guess %d)%n", goldYield.Count, guessYield.Count, goldLineId, guessLineId);
skippedGuessTrees++;
continue;
}
Tree evalGuess = tc.TransformTree(guessTree);
Tree evalGold = tc.TransformTree(goldTree);
metric.Evaluate(evalGuess, evalGold, ((Verbose) ? pwOut : null));
}
if (guessItr.MoveNext() || goldItr.MoveNext())
{
System.Console.Error.Printf("Guess/gold files do not have equal lengths (guess: %d gold: %d)%n.", guessLineId, goldLineId);
}
pwOut.Println("================================================================================");
if (skippedGuessTrees != 0)
{
pwOut.Printf("%s %d guess trees%n", "Unable to evaluate", skippedGuessTrees);
}
metric.Display(true, pwOut);
pwOut.Close();
}
/// <summary>Test the parser on a treebank.</summary>
/// <remarks>
/// Test the parser on a treebank. Parses will be written to stdout, and
/// various other information will be written to stderr and stdout,
/// particularly if <code>op.testOptions.verbose</code> is true.
/// </remarks>
/// <param name="testTreebank">The treebank to parse</param>
/// <returns>
/// The labeled precision/recall F<sub>1</sub> (EVALB measure)
/// of the parser on the treebank.
/// </returns>
public virtual double TestOnTreebank(Treebank testTreebank)
{
log.Info("Testing on treebank");
Timing treebankTotalTimer = new Timing();
TreePrint treePrint = op.testOptions.TreePrint(op.tlpParams);
ITreebankLangParserParams tlpParams = op.tlpParams;
ITreebankLanguagePack tlp = op.Langpack();
PrintWriter pwOut;
PrintWriter pwErr;
if (op.testOptions.quietEvaluation)
{
NullOutputStream quiet = new NullOutputStream();
pwOut = tlpParams.Pw(quiet);
pwErr = tlpParams.Pw(quiet);
}
else
{
pwOut = tlpParams.Pw();
pwErr = tlpParams.Pw(System.Console.Error);
}
if (op.testOptions.verbose)
{
pwErr.Print("Testing ");
pwErr.Println(testTreebank.TextualSummary(tlp));
}
if (op.testOptions.evalb)
{
EvalbFormatWriter.InitEVALBfiles(tlpParams);
}
PrintWriter pwFileOut = null;
if (op.testOptions.writeOutputFiles)
{
string fname = op.testOptions.outputFilesPrefix + "." + op.testOptions.outputFilesExtension;
try
{
pwFileOut = op.tlpParams.Pw(new FileOutputStream(fname));
}
catch (IOException ioe)
{
Sharpen.Runtime.PrintStackTrace(ioe);
}
}
PrintWriter pwStats = null;
if (op.testOptions.outputkBestEquivocation != null)
{
try
{
pwStats = op.tlpParams.Pw(new FileOutputStream(op.testOptions.outputkBestEquivocation));
}
catch (IOException ioe)
{
Sharpen.Runtime.PrintStackTrace(ioe);
}
}
if (op.testOptions.testingThreads != 1)
{
MulticoreWrapper <IList <IHasWord>, IParserQuery> wrapper = new MulticoreWrapper <IList <IHasWord>, IParserQuery>(op.testOptions.testingThreads, new ParsingThreadsafeProcessor(pqFactory, pwErr));
LinkedList <Tree> goldTrees = new LinkedList <Tree>();
foreach (Tree goldTree in testTreebank)
{
IList <IHasWord> sentence = GetInputSentence(goldTree);
goldTrees.Add(goldTree);
pwErr.Println("Parsing [len. " + sentence.Count + "]: " + SentenceUtils.ListToString(sentence));
wrapper.Put(sentence);
while (wrapper.Peek())
{
IParserQuery pq = wrapper.Poll();
goldTree = goldTrees.Poll();
ProcessResults(pq, goldTree, pwErr, pwOut, pwFileOut, pwStats, treePrint);
}
}
// for tree iterator
wrapper.Join();
while (wrapper.Peek())
{
IParserQuery pq = wrapper.Poll();
Tree goldTree_1 = goldTrees.Poll();
ProcessResults(pq, goldTree_1, pwErr, pwOut, pwFileOut, pwStats, treePrint);
}
}
else
{
IParserQuery pq = pqFactory.ParserQuery();
foreach (Tree goldTree in testTreebank)
{
IList <CoreLabel> sentence = GetInputSentence(goldTree);
pwErr.Println("Parsing [len. " + sentence.Count + "]: " + SentenceUtils.ListToString(sentence));
pq.ParseAndReport(sentence, pwErr);
ProcessResults(pq, goldTree, pwErr, pwOut, pwFileOut, pwStats, treePrint);
}
}
// for tree iterator
//Done parsing...print the results of the evaluations
treebankTotalTimer.Done("Testing on treebank");
if (op.testOptions.quietEvaluation)
{
pwErr = tlpParams.Pw(System.Console.Error);
}
if (saidMemMessage)
{
ParserUtils.PrintOutOfMemory(pwErr);
}
if (op.testOptions.evalb)
{
EvalbFormatWriter.CloseEVALBfiles();
}
if (numSkippedEvals != 0)
{
pwErr.Printf("Unable to evaluate %d parser hypotheses due to yield mismatch\n", numSkippedEvals);
}
// only created here so we know what parser types are supported...
IParserQuery pq_1 = pqFactory.ParserQuery();
if (summary)
{
if (pcfgLB != null)
{
pcfgLB.Display(false, pwErr);
}
if (pcfgChildSpecific != null)
{
pcfgChildSpecific.Display(false, pwErr);
}
if (pcfgLA != null)
{
pcfgLA.Display(false, pwErr);
}
if (pcfgCB != null)
{
pcfgCB.Display(false, pwErr);
}
if (pcfgDA != null)
{
pcfgDA.Display(false, pwErr);
}
if (pcfgTA != null)
{
pcfgTA.Display(false, pwErr);
}
if (pcfgLL != null && pq_1.GetPCFGParser() != null)
{
pcfgLL.Display(false, pwErr);
}
if (depDA != null)
{
depDA.Display(false, pwErr);
}
if (depTA != null)
{
depTA.Display(false, pwErr);
}
if (depLL != null && pq_1.GetDependencyParser() != null)
{
depLL.Display(false, pwErr);
}
if (factLB != null)
{
factLB.Display(false, pwErr);
}
if (factChildSpecific != null)
{
factChildSpecific.Display(false, pwErr);
}
if (factLA != null)
{
factLA.Display(false, pwErr);
}
if (factCB != null)
{
factCB.Display(false, pwErr);
}
if (factDA != null)
{
factDA.Display(false, pwErr);
}
if (factTA != null)
{
factTA.Display(false, pwErr);
}
if (factLL != null && pq_1.GetFactoredParser() != null)
{
factLL.Display(false, pwErr);
}
if (pcfgCatE != null)
{
pcfgCatE.Display(false, pwErr);
}
foreach (IEval eval in evals)
{
eval.Display(false, pwErr);
}
foreach (BestOfTopKEval eval_1 in topKEvals)
{
eval_1.Display(false, pwErr);
}
}
// these ones only have a display mode, so display if turned on!!
if (pcfgRUO != null)
{
pcfgRUO.Display(true, pwErr);
}
if (pcfgCUO != null)
{
pcfgCUO.Display(true, pwErr);
}
if (tsv)
{
NumberFormat nf = new DecimalFormat("0.00");
pwErr.Println("factF1\tfactDA\tfactEx\tpcfgF1\tdepDA\tfactTA\tnum");
if (factLB != null)
{
pwErr.Print(nf.Format(factLB.GetEvalbF1Percent()));
}
pwErr.Print("\t");
if (pq_1.GetDependencyParser() != null && factDA != null)
{
pwErr.Print(nf.Format(factDA.GetEvalbF1Percent()));
}
pwErr.Print("\t");
if (factLB != null)
{
pwErr.Print(nf.Format(factLB.GetExactPercent()));
}
pwErr.Print("\t");
if (pcfgLB != null)
{
pwErr.Print(nf.Format(pcfgLB.GetEvalbF1Percent()));
}
pwErr.Print("\t");
if (pq_1.GetDependencyParser() != null && depDA != null)
{
pwErr.Print(nf.Format(depDA.GetEvalbF1Percent()));
}
pwErr.Print("\t");
if (pq_1.GetPCFGParser() != null && factTA != null)
{
pwErr.Print(nf.Format(factTA.GetEvalbF1Percent()));
}
pwErr.Print("\t");
if (factLB != null)
{
pwErr.Print(factLB.GetNum());
}
pwErr.Println();
}
double f1 = 0.0;
if (factLB != null)
{
f1 = factLB.GetEvalbF1();
}
//Close files (if necessary)
if (pwFileOut != null)
{
pwFileOut.Close();
}
if (pwStats != null)
{
pwStats.Close();
}
if (parserQueryEvals != null)
{
foreach (IParserQueryEval parserQueryEval in parserQueryEvals)
{
parserQueryEval.Display(false, pwErr);
}
}
return(f1);
}
/// <param name="args"/>
public static void Main(string[] args)
{
if (args.Length < MinArgs)
{
log.Info(Usage());
System.Environment.Exit(-1);
}
Properties options = StringUtils.ArgsToProperties(args, OptionArgDefs());
bool Verbose = PropertiesUtils.GetBool(options, "v", false);
Language Language = PropertiesUtils.Get(options, "l", Language.English, typeof(Language));
int MaxGoldYield = PropertiesUtils.GetInt(options, "g", int.MaxValue);
int MaxGuessYield = PropertiesUtils.GetInt(options, "y", int.MaxValue);
string[] parsedArgs = options.GetProperty(string.Empty, string.Empty).Split("\\s+");
if (parsedArgs.Length != MinArgs)
{
log.Info(Usage());
System.Environment.Exit(-1);
}
File goldFile = new File(parsedArgs[0]);
File guessFile = new File(parsedArgs[1]);
ITreebankLangParserParams tlpp = Language.@params;
PrintWriter pwOut = tlpp.Pw();
Treebank guessTreebank = tlpp.DiskTreebank();
guessTreebank.LoadPath(guessFile);
pwOut.Println("GUESS TREEBANK:");
pwOut.Println(guessTreebank.TextualSummary());
Treebank goldTreebank = tlpp.DiskTreebank();
goldTreebank.LoadPath(goldFile);
pwOut.Println("GOLD TREEBANK:");
pwOut.Println(goldTreebank.TextualSummary());
Edu.Stanford.Nlp.Parser.Metrics.CollinsDepEval depEval = new Edu.Stanford.Nlp.Parser.Metrics.CollinsDepEval("CollinsDep", true, tlpp.HeadFinder(), tlpp.TreebankLanguagePack().StartSymbol());
ITreeTransformer tc = tlpp.Collinizer();
//PennTreeReader skips over null/malformed parses. So when the yields of the gold/guess trees
//don't match, we need to keep looking for the next gold tree that matches.
//The evalb ref implementation differs slightly as it expects one tree per line. It assigns
//status as follows:
//
// 0 - Ok (yields match)
// 1 - length mismatch
// 2 - null parse e.g. (()).
//
//In the cases of 1,2, evalb does not include the tree pair in the LP/LR computation.
IEnumerator <Tree> goldItr = goldTreebank.GetEnumerator();
int goldLineId = 0;
int skippedGuessTrees = 0;
foreach (Tree guess in guessTreebank)
{
Tree evalGuess = tc.TransformTree(guess);
if (guess.Yield().Count > MaxGuessYield)
{
skippedGuessTrees++;
continue;
}
bool doneEval = false;
while (goldItr.MoveNext() && !doneEval)
{
Tree gold = goldItr.Current;
Tree evalGold = tc.TransformTree(gold);
goldLineId++;
if (gold.Yield().Count > MaxGoldYield)
{
continue;
}
else
{
if (evalGold.Yield().Count != evalGuess.Yield().Count)
{
pwOut.Println("Yield mismatch at gold line " + goldLineId);
skippedGuessTrees++;
break;
}
}
//Default evalb behavior -- skip this guess tree
depEval.Evaluate(evalGuess, evalGold, ((Verbose) ? pwOut : null));
doneEval = true;
}
}
//Move to the next guess parse
pwOut.Println("================================================================================");
if (skippedGuessTrees != 0)
{
pwOut.Printf("%s %d guess trees\n", ((MaxGuessYield < int.MaxValue) ? "Skipped" : "Unable to evaluate"), skippedGuessTrees);
}
depEval.Display(true, pwOut);
pwOut.Close();
}