/// <summary>Mark twin mentions: All mention boundaries should be matched</summary>
private void FindTwinMentionsStrict()
{
for (int sentNum = 0; sentNum < goldOrderedMentionsBySentence.Count; sentNum++)
{
IList <Mention> golds = goldOrderedMentionsBySentence[sentNum];
IList <Mention> predicts = predictedOrderedMentionsBySentence[sentNum];
// For CoNLL training there are some documents with gold mentions with the same position offsets
// See /scr/nlp/data/conll-2011/v2/data/train/data/english/annotations/nw/wsj/09/wsj_0990.v2_auto_conll
// (Packwood - Roth)
CollectionValuedMap <IntPair, Mention> goldMentionPositions = new CollectionValuedMap <IntPair, Mention>();
foreach (Mention g in golds)
{
IntPair ip = new IntPair(g.startIndex, g.endIndex);
if (goldMentionPositions.Contains(ip))
{
StringBuilder existingMentions = new StringBuilder();
foreach (Mention eg in goldMentionPositions[ip])
{
if (existingMentions.Length > 0)
{
existingMentions.Append(",");
}
existingMentions.Append(eg.mentionID);
}
SieveCoreferenceSystem.logger.Warning("WARNING: gold mentions with the same offsets: " + ip + " mentions=" + g.mentionID + "," + existingMentions + ", " + g.SpanToString());
}
//assert(!goldMentionPositions.containsKey(ip));
goldMentionPositions.Add(new IntPair(g.startIndex, g.endIndex), g);
}
foreach (Mention p in predicts)
{
IntPair pos = new IntPair(p.startIndex, p.endIndex);
if (goldMentionPositions.Contains(pos))
{
ICollection <Mention> cm = goldMentionPositions[pos];
Mention g_1 = cm.GetEnumerator().Current;
cm.Remove(g_1);
p.mentionID = g_1.mentionID;
p.twinless = false;
g_1.twinless = false;
}
}
// temp: for making easy to recognize twinless mention
foreach (Mention p_1 in predicts)
{
if (p_1.twinless)
{
p_1.mentionID += 10000;
}
}
}
}
/// <exception cref="System.Exception"/>
private static void DescendantsHelper(SemanticGraph g, IndexedWord curr, ICollection <IndexedWord> descendantSet, IList <string> allCutOffRels, IList <IndexedWord> doNotAddThese, IList <IndexedWord> seenNodes, bool ignoreCommonTags, IPredicate <CoreLabel
> acceptWord, CollectionValuedMap <int, string> feat)
{
if (seenNodes.Contains(curr))
{
return;
}
seenNodes.Add(curr);
if (descendantSet.Contains(curr) || (doNotAddThese != null && doNotAddThese.Contains(curr)) || !acceptWord.Test(curr.BackingLabel()))
{
return;
}
if (!ignoreCommonTags || !ignoreTags.Contains(curr.Tag().Trim()))
{
descendantSet.Add(curr);
}
foreach (IndexedWord child in g.GetChildren(curr))
{
bool dontuse = false;
if (doNotAddThese != null && doNotAddThese.Contains(child))
{
dontuse = true;
}
GrammaticalRelation rel = null;
if (dontuse == false)
{
rel = g.Reln(curr, child);
dontuse = CheckIfSatisfiesRelConstrains(g, curr, child, allCutOffRels, rel);
}
if (dontuse == false)
{
foreach (string cutOffTagRegex in cutoffTags)
{
if (child.Tag().Matches(cutOffTagRegex))
{
if (Debug >= 5)
{
System.Console.Out.WriteLine("ignored tag " + child + " because it satisfied " + cutOffTagRegex);
}
dontuse = true;
break;
}
}
}
if (dontuse == false)
{
if (!feat.Contains(curr.Index()))
{
feat[curr.Index()] = new List <string>();
}
GetPatternsFromDataMultiClass.GetFeatures(g, curr, false, feat[curr.Index()], rel);
//feat.add(curr.index(), "REL-" + rel.getShortName());
DescendantsHelper(g, child, descendantSet, allCutOffRels, doNotAddThese, seenNodes, ignoreCommonTags, acceptWord, feat);
}
}
}