/// <exception cref="System.IO.IOException"/>
internal virtual byte[] GetProtoBufAnnotation(IList <CoreLabel> tokens)
{
ByteArrayOutputStream os = new ByteArrayOutputStream();
foreach (CoreLabel token in tokens)
{
CoreNLPProtos.Token ptoken = p.ToProto(token);
ptoken.WriteDelimitedTo(os);
}
os.Flush();
return(os.ToByteArray());
}
/// <exception cref="Edu.Stanford.Nlp.Pipeline.WebServiceAnnotator.ShouldRetryException"/>
/// <exception cref="Edu.Stanford.Nlp.Pipeline.WebServiceAnnotator.PermanentlyFailedException"/>
protected internal override void AnnotateImpl(Annotation ann)
{
Annotation ann_;
// New annotaiton
try
{
// Executes the connection from conn
HttpURLConnection conn;
conn = (HttpURLConnection) new URL(annotatorEndpoint + "/annotate/").OpenConnection();
conn.SetRequestMethod("POST");
conn.SetDoOutput(true);
conn.SetRequestProperty("Content-Type", "application/octet-stream; charset=UTF-8");
using (OutputStream outputStream = conn.GetOutputStream())
{
serializer.ToProto(ann).WriteDelimitedTo(outputStream);
outputStream.Flush();
}
conn.Connect();
try
{
using (InputStream inputStream = conn.GetInputStream())
{
Pair <Annotation, InputStream> pair = serializer.Read(inputStream);
ann_ = pair.first;
}
}
catch (Exception e)
{
throw new WebServiceAnnotator.PermanentlyFailedException(e);
}
}
catch (MalformedURLException e)
{
throw new WebServiceAnnotator.PermanentlyFailedException(e);
}
catch (IOException)
{
throw new WebServiceAnnotator.ShouldRetryException();
}
// Copy over annotation.
Copy(ann_, ann);
}
/// <summary>Annotate this document for KBP relations.</summary>
/// <param name="annotation">The document to annotate.</param>
public virtual void Annotate(Annotation annotation)
{
// get a list of sentences for this annotation
IList <ICoreMap> sentences = annotation.Get(typeof(CoreAnnotations.SentencesAnnotation));
// Create simple document
Document doc = new Document(kbpProperties, serializer.ToProto(annotation));
// Get the mentions in the document
IList <ICoreMap> mentions = new List <ICoreMap>();
foreach (ICoreMap sentence in sentences)
{
Sharpen.Collections.AddAll(mentions, sentence.Get(typeof(CoreAnnotations.MentionsAnnotation)));
}
// Compute coreferent clusters
// (map an index to a KBP mention)
IDictionary <Pair <int, int>, ICoreMap> mentionByStartIndex = new Dictionary <Pair <int, int>, ICoreMap>();
foreach (ICoreMap mention in mentions)
{
foreach (CoreLabel token in mention.Get(typeof(CoreAnnotations.TokensAnnotation)))
{
mentionByStartIndex[Pair.MakePair(token.SentIndex(), token.Index())] = mention;
}
}
// (collect coreferent KBP mentions)
IDictionary <ICoreMap, ICollection <ICoreMap> > mentionsMap = new Dictionary <ICoreMap, ICollection <ICoreMap> >();
// map from canonical mention -> other mentions
if (annotation.Get(typeof(CorefCoreAnnotations.CorefChainAnnotation)) != null)
{
foreach (KeyValuePair <int, CorefChain> chain in annotation.Get(typeof(CorefCoreAnnotations.CorefChainAnnotation)))
{
ICoreMap firstMention = null;
foreach (CorefChain.CorefMention mention_1 in chain.Value.GetMentionsInTextualOrder())
{
ICoreMap kbpMention = null;
for (int i = mention_1.startIndex; i < mention_1.endIndex; ++i)
{
if (mentionByStartIndex.Contains(Pair.MakePair(mention_1.sentNum - 1, i)))
{
kbpMention = mentionByStartIndex[Pair.MakePair(mention_1.sentNum - 1, i)];
break;
}
}
if (firstMention == null)
{
firstMention = kbpMention;
}
if (kbpMention != null)
{
if (!mentionsMap.Contains(firstMention))
{
mentionsMap[firstMention] = new LinkedHashSet <ICoreMap>();
}
mentionsMap[firstMention].Add(kbpMention);
}
}
}
}
// (coreference acronyms)
AcronymMatch(mentions, mentionsMap);
// (ensure valid NER tag for canonical mention)
foreach (ICoreMap key in new HashSet <ICoreMap>(mentionsMap.Keys))
{
if (key.Get(typeof(CoreAnnotations.NamedEntityTagAnnotation)) == null)
{
ICoreMap newKey = null;
foreach (ICoreMap candidate in mentionsMap[key])
{
if (candidate.Get(typeof(CoreAnnotations.NamedEntityTagAnnotation)) != null)
{
newKey = candidate;
break;
}
}
if (newKey != null)
{
mentionsMap[newKey] = Sharpen.Collections.Remove(mentionsMap, key);
}
else
{
Sharpen.Collections.Remove(mentionsMap, key);
}
}
}
// case: no mention in this chain has an NER tag.
// Propagate Entity Link
foreach (KeyValuePair <ICoreMap, ICollection <ICoreMap> > entry in mentionsMap)
{
string entityLink = entry.Key.Get(typeof(CoreAnnotations.WikipediaEntityAnnotation));
if (entityLink != null)
{
foreach (ICoreMap mention_1 in entry.Value)
{
foreach (CoreLabel token in mention_1.Get(typeof(CoreAnnotations.TokensAnnotation)))
{
token.Set(typeof(CoreAnnotations.WikipediaEntityAnnotation), entityLink);
}
}
}
}
// create a mapping of char offset pairs to KBPMention
Dictionary <Pair <int, int>, ICoreMap> charOffsetToKBPMention = new Dictionary <Pair <int, int>, ICoreMap>();
foreach (ICoreMap mention_2 in mentions)
{
int nerMentionCharBegin = mention_2.Get(typeof(CoreAnnotations.CharacterOffsetBeginAnnotation));
int nerMentionCharEnd = mention_2.Get(typeof(CoreAnnotations.CharacterOffsetEndAnnotation));
charOffsetToKBPMention[new Pair <int, int>(nerMentionCharBegin, nerMentionCharEnd)] = mention_2;
}
// Create a canonical mention map
IDictionary <ICoreMap, ICoreMap> mentionToCanonicalMention;
if (kbpLanguage.Equals(LanguageInfo.HumanLanguage.Spanish))
{
mentionToCanonicalMention = spanishCorefSystem.CanonicalMentionMapFromEntityMentions(mentions);
if (Verbose)
{
log.Info("---");
log.Info("basic spanish coref results");
foreach (ICoreMap originalMention in mentionToCanonicalMention.Keys)
{
if (!originalMention.Equals(mentionToCanonicalMention[originalMention]))
{
log.Info("mapped: " + originalMention + " to: " + mentionToCanonicalMention[originalMention]);
}
}
}
}
else
{
mentionToCanonicalMention = new Dictionary <ICoreMap, ICoreMap>();
}
// check if there is coref info
ICollection <KeyValuePair <int, CorefChain> > corefChains;
if (annotation.Get(typeof(CorefCoreAnnotations.CorefChainAnnotation)) != null && !kbpLanguage.Equals(LanguageInfo.HumanLanguage.Spanish))
{
corefChains = annotation.Get(typeof(CorefCoreAnnotations.CorefChainAnnotation));
}
else
{
corefChains = new HashSet <KeyValuePair <int, CorefChain> >();
}
foreach (KeyValuePair <int, CorefChain> indexCorefChainPair in corefChains)
{
CorefChain corefChain = indexCorefChainPair.Value;
Pair <IList <ICoreMap>, ICoreMap> corefChainKBPMentionsAndBestIndex = CorefChainToKBPMentions(corefChain, annotation, charOffsetToKBPMention);
IList <ICoreMap> corefChainKBPMentions = corefChainKBPMentionsAndBestIndex.First();
ICoreMap bestKBPMentionForChain = corefChainKBPMentionsAndBestIndex.Second();
if (bestKBPMentionForChain != null)
{
foreach (ICoreMap kbpMention in corefChainKBPMentions)
{
if (kbpMention != null)
{
//System.err.println("---");
// ad hoc filters ; assume acceptable unless a filter blocks it
bool acceptableLink = true;
// block people matches without a token overlap, exempting pronominal to non-pronominal
// good: Ashton --> Catherine Ashton
// good: she --> Catherine Ashton
// bad: Morsi --> Catherine Ashton
string kbpMentionNERTag = kbpMention.Get(typeof(CoreAnnotations.NamedEntityTagAnnotation));
string bestKBPMentionForChainNERTag = bestKBPMentionForChain.Get(typeof(CoreAnnotations.NamedEntityTagAnnotation));
if (kbpMentionNERTag != null && bestKBPMentionForChainNERTag != null && kbpMentionNERTag.Equals("PERSON") && bestKBPMentionForChainNERTag.Equals("PERSON") && !KbpIsPronominalMention(kbpMention.Get(typeof(CoreAnnotations.TokensAnnotation))[0]
) && !KbpIsPronominalMention(bestKBPMentionForChain.Get(typeof(CoreAnnotations.TokensAnnotation))[0]))
{
//System.err.println("testing PERSON to PERSON coref link");
bool tokenMatchFound = false;
foreach (CoreLabel kbpToken in kbpMention.Get(typeof(CoreAnnotations.TokensAnnotation)))
{
foreach (CoreLabel bestKBPToken in bestKBPMentionForChain.Get(typeof(CoreAnnotations.TokensAnnotation)))
{
if (kbpToken.Word().ToLower().Equals(bestKBPToken.Word().ToLower()))
{
tokenMatchFound = true;
break;
}
}
if (tokenMatchFound)
{
break;
}
}
if (!tokenMatchFound)
{
acceptableLink = false;
}
}
// check the coref link passed the filters
if (acceptableLink)
{
mentionToCanonicalMention[kbpMention] = bestKBPMentionForChain;
}
}
}
}
}
//System.err.println("kbp mention: " + kbpMention.get(CoreAnnotations.TextAnnotation.class));
//System.err.println("coref mention: " + bestKBPMentionForChain.get(CoreAnnotations.TextAnnotation.class));
// (add missing mentions)
mentions.Stream().Filter(null).ForEach(null);
// handle acronym coreference
Dictionary <string, IList <ICoreMap> > acronymClusters = new Dictionary <string, IList <ICoreMap> >();
Dictionary <string, IList <ICoreMap> > acronymInstances = new Dictionary <string, IList <ICoreMap> >();
foreach (ICoreMap acronymMention in mentionToCanonicalMention.Keys)
{
string acronymNERTag = acronymMention.Get(typeof(CoreAnnotations.NamedEntityTagAnnotation));
if ((acronymMention == mentionToCanonicalMention[acronymMention]) && acronymNERTag != null && (acronymNERTag.Equals(KBPRelationExtractor.NERTag.Organization.name) || acronymNERTag.Equals(KBPRelationExtractor.NERTag.Location.name)))
{
string acronymText = acronymMention.Get(typeof(CoreAnnotations.TextAnnotation));
IList <ICoreMap> coreferentMentions = new List <ICoreMap>();
// define acronyms as not containing spaces (e.g. ACLU)
if (!acronymText.Contains(" "))
{
int numCoreferentsChecked = 0;
foreach (ICoreMap coreferentMention in mentions)
{
// only check first 1000
if (numCoreferentsChecked > 1000)
{
break;
}
// don't check a mention against itself
if (acronymMention == coreferentMention)
{
continue;
}
// don't check other mentions without " "
string coreferentText = coreferentMention.Get(typeof(CoreAnnotations.TextAnnotation));
if (!coreferentText.Contains(" "))
{
continue;
}
numCoreferentsChecked++;
IList <string> coreferentTokenStrings = coreferentMention.Get(typeof(CoreAnnotations.TokensAnnotation)).Stream().Map(null).Collect(Collectors.ToList());
// when an acronym match is found:
// store every mention (that isn't ACLU) that matches with ACLU in acronymClusters
// store every instance of "ACLU" in acronymInstances
// afterwards find the best mention in acronymClusters, and match it to every mention in acronymInstances
if (AcronymMatcher.IsAcronym(acronymText, coreferentTokenStrings))
{
if (!acronymClusters.Contains(acronymText))
{
acronymClusters[acronymText] = new List <ICoreMap>();
}
if (!acronymInstances.Contains(acronymText))
{
acronymInstances[acronymText] = new List <ICoreMap>();
}
acronymClusters[acronymText].Add(coreferentMention);
acronymInstances[acronymText].Add(acronymMention);
}
}
}
}
}
// process each acronym (e.g. ACLU)
foreach (string acronymText_1 in acronymInstances.Keys)
{
// find longest ORG or null
ICoreMap bestORG = null;
foreach (ICoreMap coreferentMention in acronymClusters[acronymText_1])
{
if (!coreferentMention.Get(typeof(CoreAnnotations.NamedEntityTagAnnotation)).Equals(KBPRelationExtractor.NERTag.Organization.name))
{
continue;
}
if (bestORG == null)
{
bestORG = coreferentMention;
}
else
{
if (coreferentMention.Get(typeof(CoreAnnotations.TextAnnotation)).Length > bestORG.Get(typeof(CoreAnnotations.TextAnnotation)).Length)
{
bestORG = coreferentMention;
}
}
}
// find longest LOC or null
ICoreMap bestLOC = null;
foreach (ICoreMap coreferentMention_1 in acronymClusters[acronymText_1])
{
if (!coreferentMention_1.Get(typeof(CoreAnnotations.NamedEntityTagAnnotation)).Equals(KBPRelationExtractor.NERTag.Location.name))
{
continue;
}
if (bestLOC == null)
{
bestLOC = coreferentMention_1;
}
else
{
if (coreferentMention_1.Get(typeof(CoreAnnotations.TextAnnotation)).Length > bestLOC.Get(typeof(CoreAnnotations.TextAnnotation)).Length)
{
bestLOC = coreferentMention_1;
}
}
}
// link ACLU to "American Civil Liberties Union" ; make sure NER types match
foreach (ICoreMap acronymMention_1 in acronymInstances[acronymText_1])
{
string mentionType = acronymMention_1.Get(typeof(CoreAnnotations.NamedEntityTagAnnotation));
if (mentionType.Equals(KBPRelationExtractor.NERTag.Organization.name) && bestORG != null)
{
mentionToCanonicalMention[acronymMention_1] = bestORG;
}
if (mentionType.Equals(KBPRelationExtractor.NERTag.Location.name) && bestLOC != null)
{
mentionToCanonicalMention[acronymMention_1] = bestLOC;
}
}
}
// Cluster mentions by sentence
IList <ICoreMap>[] mentionsBySentence = new IList[annotation.Get(typeof(CoreAnnotations.SentencesAnnotation)).Count];
for (int i_1 = 0; i_1 < mentionsBySentence.Length; ++i_1)
{
mentionsBySentence[i_1] = new List <ICoreMap>();
}
foreach (ICoreMap mention_3 in mentionToCanonicalMention.Keys)
{
mentionsBySentence[mention_3.Get(typeof(CoreAnnotations.SentenceIndexAnnotation))].Add(mention_3);
}
// Classify
for (int sentenceI = 0; sentenceI < mentionsBySentence.Length; ++sentenceI)
{
Dictionary <string, RelationTriple> relationStringsToTriples = new Dictionary <string, RelationTriple>();
IList <RelationTriple> finalTriplesList = new List <RelationTriple>();
// the annotations
IList <ICoreMap> candidates = mentionsBySentence[sentenceI];
// determine sentence length
int sentenceLength = annotation.Get(typeof(CoreAnnotations.SentencesAnnotation))[sentenceI].Get(typeof(CoreAnnotations.TokensAnnotation)).Count;
// check if sentence is too long, if it's too long don't run kbp
if (maxLength != -1 && sentenceLength > maxLength)
{
// set the triples annotation to an empty list of RelationTriples
annotation.Get(typeof(CoreAnnotations.SentencesAnnotation))[sentenceI].Set(typeof(CoreAnnotations.KBPTriplesAnnotation), finalTriplesList);
// continue to next sentence
continue;
}
// sentence isn't too long, so continue processing this sentence
for (int subjI = 0; subjI < candidates.Count; ++subjI)
{
ICoreMap subj = candidates[subjI];
int subjBegin = subj.Get(typeof(CoreAnnotations.TokensAnnotation))[0].Index() - 1;
int subjEnd = subj.Get(typeof(CoreAnnotations.TokensAnnotation))[subj.Get(typeof(CoreAnnotations.TokensAnnotation)).Count - 1].Index();
Optional <KBPRelationExtractor.NERTag> subjNER = KBPRelationExtractor.NERTag.FromString(subj.Get(typeof(CoreAnnotations.NamedEntityTagAnnotation)));
if (subjNER.IsPresent())
{
for (int objI = 0; objI < candidates.Count; ++objI)
{
if (subjI == objI)
{
continue;
}
if (Thread.Interrupted())
{
throw new RuntimeInterruptedException();
}
ICoreMap obj = candidates[objI];
int objBegin = obj.Get(typeof(CoreAnnotations.TokensAnnotation))[0].Index() - 1;
int objEnd = obj.Get(typeof(CoreAnnotations.TokensAnnotation))[obj.Get(typeof(CoreAnnotations.TokensAnnotation)).Count - 1].Index();
Optional <KBPRelationExtractor.NERTag> objNER = KBPRelationExtractor.NERTag.FromString(obj.Get(typeof(CoreAnnotations.NamedEntityTagAnnotation)));
if (objNER.IsPresent() && KBPRelationExtractor.RelationType.PlausiblyHasRelation(subjNER.Get(), objNER.Get()))
{
// type check
KBPRelationExtractor.KBPInput input = new KBPRelationExtractor.KBPInput(new Span(subjBegin, subjEnd), new Span(objBegin, objEnd), subjNER.Get(), objNER.Get(), doc.Sentence(sentenceI));
// -- BEGIN Classify
Pair <string, double> prediction = extractor.Classify(input);
// -- END Classify
// Handle the classifier output
if (!KBPStatisticalExtractor.NoRelation.Equals(prediction.first))
{
RelationTriple triple = new RelationTriple.WithLink(subj.Get(typeof(CoreAnnotations.TokensAnnotation)), mentionToCanonicalMention[subj].Get(typeof(CoreAnnotations.TokensAnnotation)), Java.Util.Collections.SingletonList(new CoreLabel(new Word
(ConvertRelationNameToLatest(prediction.first)))), obj.Get(typeof(CoreAnnotations.TokensAnnotation)), mentionToCanonicalMention[obj].Get(typeof(CoreAnnotations.TokensAnnotation)), prediction.second, sentences[sentenceI].Get(typeof(SemanticGraphCoreAnnotations.CollapsedCCProcessedDependenciesAnnotation
)), subj.Get(typeof(CoreAnnotations.WikipediaEntityAnnotation)), obj.Get(typeof(CoreAnnotations.WikipediaEntityAnnotation)));
string tripleString = triple.SubjectGloss() + "\t" + triple.RelationGloss() + "\t" + triple.ObjectGloss();
// ad hoc checks for problems
bool acceptableTriple = true;
if (triple.ObjectGloss().Equals(triple.SubjectGloss()) && triple.RelationGloss().EndsWith("alternate_names"))
{
acceptableTriple = false;
}
// only add this triple if it has the highest confidence ; this process generates duplicates with
// different confidence scores, so we want to filter out the lower confidence versions
if (acceptableTriple && !relationStringsToTriples.Contains(tripleString))
{
relationStringsToTriples[tripleString] = triple;
}
else
{
if (acceptableTriple && triple.confidence > relationStringsToTriples[tripleString].confidence)
{
relationStringsToTriples[tripleString] = triple;
}
}
}
}
}
}
}
finalTriplesList = new ArrayList(relationStringsToTriples.Values);
// Set triples
annotation.Get(typeof(CoreAnnotations.SentencesAnnotation))[sentenceI].Set(typeof(CoreAnnotations.KBPTriplesAnnotation), finalTriplesList);
}
}