def getTokenFeatures(self, token, sentenceGraph): """ Returns a list of features based on the attributes of a token. These can be used to define more complex features. """ # These features are cached when this method is first called # for a token. if self.tokenFeatures.has_key(token): return self.tokenFeatures[token] tokTxt=sentenceGraph.getTokenText(token) features = {} features["_txt_"+tokTxt]=1 features["_POS_"+token.get("POS")]=1 if self.styles["speculation_words"]: if tokTxt in self.specWords: features["_spec"]=1 features["_spec_"+tokTxt]=1 tokStem = PorterStemmer.stem(tokTxt) if tokStem in self.specWordStems: features["_spec_stem"]=1 features["_spec_stem_"+tokStem]=1 if sentenceGraph.tokenIsName[token]: features["_given"]=1 for entity in sentenceGraph.tokenIsEntityHead[token]: if entity.get("given") == "True": features["_annType_"+entity.get("type")]=1 if self.gazetteer and tokTxt.lower() in self.gazetteer: for label,weight in self.gazetteer[tokTxt.lower()].items(): pass #features["_knownLabel_"+label]=weight self.tokenFeatures[token] = features return features
def getTokenFeatures(self, token, sentenceGraph): """ Returns a list of features based on the attributes of a token. These can be used to define more complex features. """ # These features are cached when this method is first called # for a token. if self.tokenFeatures.has_key(token): return self.tokenFeatures[token] tokTxt = sentenceGraph.getTokenText(token) features = {} features["_txt_" + tokTxt] = 1 features["_POS_" + token.get("POS")] = 1 if self.styles["speculation_words"]: if tokTxt in self.specWords: features["_spec"] = 1 features["_spec_" + tokTxt] = 1 tokStem = PorterStemmer.stem(tokTxt) if tokStem in self.specWordStems: features["_spec_stem"] = 1 features["_spec_stem_" + tokStem] = 1 if sentenceGraph.tokenIsName[token]: features["_given"] = 1 for entity in sentenceGraph.tokenIsEntityHead[token]: if entity.get("given") == "True": features["_annType_" + entity.get("type")] = 1 if self.gazetteer and tokTxt.lower() in self.gazetteer: for label, weight in self.gazetteer[tokTxt.lower()].items(): pass #features["_knownLabel_"+label]=weight self.tokenFeatures[token] = features return features
def mapSplits(splits, string, stringOffset): """ Maps substrings to a string, and stems them """ begin = 0 tuples = [] for split in splits: offset = string.find(split, begin) assert offset != -1 tuples.append( (split, PorterStemmer.stem(split), (offset,len(split))) ) begin = offset + len(split) return tuples
def getTokenFeatures(self, token, sentenceGraph, text=True, POS=True, annotatedType=True, stem=False, ontology=True): """ Token features are features describing an isolated word token. These subfeatures are often merged into such features like n-grams. This method produces and caches a set of feature names for a token in the sentenceGraph sentence. The various flags can be used to choose which attributes will be included in the feature name list. @type token: cElementTree.Element @param token: a word token @type sentenceGraph: SentenceGraph @param sentenceGraph: the sentence to which the token belongs @type text: boolean @type POS: boolean @type annotatedType: boolean @type stem: boolean @type ontology: boolean """ callId = token.get("id") + str(text) + str(POS) + str(annotatedType) + str(stem) + str(ontology) if self.tokenFeatures.has_key(callId): return self.tokenFeatures[callId] featureList = [] if text: featureList.append("txt_"+sentenceGraph.getTokenText(token)) if (not self.maskNamedEntities) and sentenceGraph.tokenIsName[token]: featureList.append("txt_"+token.get("text")) if POS: pos = token.get("POS") if pos.find("_") != None and self.maximum: for split in pos.split("_"): featureList.append("POS_"+split) featureList.append("POS_"+pos) #if self.getPOSSuperType(pos) != "": # featureList.append("POSX_"+self.getPOSSuperType(pos)) if annotatedType and not self.noAnnType: annTypes = self.getTokenAnnotatedType(token, sentenceGraph) if "noAnnType" in annTypes and not self.maximum: annTypes.remove("noAnnType") for annType in annTypes: featureList.append("annType_"+annType) if ontology and (self.ontologyFeatureBuilder != None): for annType in annTypes: featureList.extend(self.ontologyFeatureBuilder.getParents(annType)) if stem: featureList.append("stem_" + PorterStemmer.stem(sentenceGraph.getTokenText(token))) if self.style != None and self.style["metamap"]: metamapFeatureDict = {} self.getMetaMapFeatures(token, sentenceGraph, metamapFeatureDict) featureList.extend(sorted(metamapFeatureDict.keys())) self.tokenFeatures[callId] = featureList return featureList
def mapSplits(splits, string, stringOffset): """ Maps substrings to a string, and stems them """ begin = 0 tuples = [] for split in splits: offset = string.find(split, begin) assert offset != -1 tuples.append((split, PorterStemmer.stem(split), (offset, len(split)))) begin = offset + len(split) return tuples
def readWords(words): if type(words) in types.StringTypes: wordSet = set() f = open(filename) for line in f.readlines(): wordSet.add(line.strip()) f.close() else: # assume it's a list wordSet = set(words) stemSet = set() for word in wordSet: stemSet.add(PorterStemmer.stem(word)) return wordSet, stemSet
def getTriggers(corpus): """ Returns a dictionary of "entity type"->"entity text"->"count" """ corpus = ETUtils.ETFromObj(corpus) trigDict = {} for entity in corpus.getroot().getiterator("entity"): if entity.get("isName") == "True": continue eType = entity.get("type") if not trigDict.has_key(eType): trigDict[eType] = {} eText = entity.get("text") eText = PorterStemmer.stem(eText) if not trigDict[eType].has_key(eText): trigDict[eType][eText] = 0 trigDict[eType][eText] += 1 return trigDict
def getTriggers(corpus): """ Returns a dictionary of "entity type"->"entity text"->"count" """ corpus = ETUtils.ETFromObj(corpus) trigDict = {} for entity in corpus.getroot().getiterator("entity"): if entity.get("given") == "True": continue eType = entity.get("type") if not trigDict.has_key(eType): trigDict[eType] = {} eText = entity.get("text") eText = PorterStemmer.stem(eText) if not trigDict[eType].has_key(eText): trigDict[eType][eText] = 0 trigDict[eType][eText] += 1 return trigDict
def buildFeatures(self, token, linear=True, chains=True): sentenceGraph = self.sentenceGraph tokenIndex = None for i in range(len(self.sentenceGraph.tokens)): if token == self.sentenceGraph.tokens[i]: tokenIndex = i break assert tokenIndex != None token = self.sentenceGraph.tokens[tokenIndex] #if not "names" in self.styles: self.setFeature(self.namedEntityCountFeature, 1) #self.features.update(self.bowFeatures) # Note! these do not get tagged # for j in range(len(sentenceGraph.tokens)): # text = "bow_" + sentenceGraph.tokens[j].get("text") # if j < i: # features[self.featureSet.getId("bf_" + text)] = 1 # elif j > i: # features[self.featureSet.getId("af_" + text)] = 1 # Main features text = token.get("text") self.setFeature("txt_" + text, 1) self.setFeature("POS_" + token.get("POS"), 1) stem = PorterStemmer.stem(text) self.setFeature("stem_" + stem, 1) self.setFeature("nonstem_" + text[len(stem):], 1) # Linear order features if linear: for index in [-3, -2, -1, 1, 2, 3]: if i + index > 0 and i + index < len(sentenceGraph.tokens): self.buildLinearOrderFeatures(sentenceGraph, i + index, str(index)) # Content if i > 0 and text[0].isalpha() and text[0].isupper(): self.setFeature("upper_case_start", 1) for j in range(len(text)): if j > 0 and text[j].isalpha() and text[j].isupper(): self.setFeature("upper_case_middle", 1) # numbers and special characters if text[j].isdigit(): self.setFeature("has_digits", 1) if j > 0 and text[j - 1] == "-": self.setFeature("has_hyphenated_digit", 1) elif text[j] == "-": self.setFeature("has_hyphen", 1) elif text[j] == "/": self.setFeature("has_fslash", 1) elif text[j] == "\\": self.setFeature("has_bslash", 1) # duplets if j > 0: self.setFeature("dt_" + text[j - 1:j + 1].lower(), 1) # triplets if j > 1: self.setFeature("tt_" + text[j - 2:j + 1].lower(), 1) # chains if chains: self.buildChains(token, sentenceGraph)
def buildExamplesFromGraph(self, sentenceGraph, outfile, goldGraph=None, structureAnalyzer=None): """ Build one example for each token of the sentence """ if sentenceGraph.sentenceElement.get("origId") in self.skiplist: print >> sys.stderr, "Skipping sentence", sentenceGraph.sentenceElement.get("origId") return 0 #[] #examples = [] exampleIndex = 0 self.tokenFeatures = {} self.tokenFeatureWeights = {} # determine (manually or automatically) the setting for whether sentences with no given entities should be skipped buildForNameless = False if structureAnalyzer and not structureAnalyzer.hasGroupClass("GIVEN", "ENTITY"): # no given entities points to no separate NER program being used buildForNameless = True if self.styles["build_for_nameless"]: # manually force the setting buildForNameless = True if self.styles["skip_for_nameless"]: # manually force the setting buildForNameless = False # determine whether sentences with no given entities should be skipped namedEntityHeadTokens = [] if not self.styles["names"]: namedEntityCount = 0 for entity in sentenceGraph.entities: if entity.get("given") == "True": # known data which can be used for features namedEntityCount += 1 namedEntityCountFeature = "nameCount_" + str(namedEntityCount) # NOTE!!! This will change the number of examples and omit # all triggers (positive and negative) from sentences which # have no NE:s, possibly giving a too-optimistic performance # value. Such sentences can still have triggers from intersentence # interactions, but as such events cannot be recovered anyway, # looking for these triggers would be pointless. if namedEntityCount == 0 and not buildForNameless: # no names, no need for triggers return 0 #[] if self.styles["pos_pairs"]: namedEntityHeadTokens = self.getNamedEntityHeadTokens(sentenceGraph) else: for key in sentenceGraph.tokenIsName.keys(): sentenceGraph.tokenIsName[key] = False bagOfWords = {} for token in sentenceGraph.tokens: text = "bow_" + token.get("text") if not bagOfWords.has_key(text): bagOfWords[text] = 0 bagOfWords[text] += 1 if sentenceGraph.tokenIsName[token]: text = "ne_" + text if not bagOfWords.has_key(text): bagOfWords[text] = 0 bagOfWords[text] += 1 bowFeatures = {} for k in sorted(bagOfWords.keys()): bowFeatures[self.featureSet.getId(k)] = bagOfWords[k] self.inEdgesByToken = {} self.outEdgesByToken = {} self.edgeSetByToken = {} for token in sentenceGraph.tokens: #inEdges = sentenceGraph.dependencyGraph.in_edges(token, data=True) #fixedInEdges = [] #for edge in inEdges: # fixedInEdges.append( (edge[0], edge[1], edge[2]["element"]) ) #inEdges = fixedInEdges inEdges = sentenceGraph.dependencyGraph.getInEdges(token) #inEdges.sort(compareDependencyEdgesById) self.inEdgesByToken[token] = inEdges #outEdges = sentenceGraph.dependencyGraph.out_edges(token, data=True) #fixedOutEdges = [] #for edge in outEdges: # fixedOutEdges.append( (edge[0], edge[1], edge[2]["element"]) ) #outEdges = fixedOutEdges outEdges = sentenceGraph.dependencyGraph.getOutEdges(token) #outEdges.sort(compareDependencyEdgesById) self.outEdgesByToken[token] = outEdges self.edgeSetByToken[token] = set(inEdges + outEdges) for i in range(len(sentenceGraph.tokens)): token = sentenceGraph.tokens[i] # CLASS if len(sentenceGraph.tokenIsEntityHead[token]) > 0: categoryName, entityIds = self.getMergedEntityType(sentenceGraph.tokenIsEntityHead[token]) else: categoryName, entityIds = "neg", None self.exampleStats.beginExample(categoryName) # Recognize only non-named entities (i.e. interaction words) if sentenceGraph.tokenIsName[token] and not self.styles["names"] and not self.styles["all_tokens"]: self.exampleStats.filter("name") self.exampleStats.endExample() continue # if "selftrain_limits" in self.styles: # # any predicted entity not part of the self-training set causes example to be rejected # filtered = False # for entity in sentenceGraph.tokenIsEntityHead[token]: # if entity.get("selftrain") == "False": # self.exampleStats.filter("selftrain_limits") # self.exampleStats.endExample() # filtered = True # break # if filtered: # continue # if "selftrain_group" in self.styles: # # any predicted entity not part of the self-training set causes example to be rejected # filtered = False # for entity in sentenceGraph.tokenIsEntityHead[token]: # if entity.get("selftraingroup") not in self.selfTrainGroups: # self.exampleStats.filter("selftrain_group") # self.exampleStats.endExample() # filtered = True # break # if filtered: # continue if self.styles["pos_only"] and categoryName == "neg": self.exampleStats.filter("pos_only") self.exampleStats.endExample() continue category = self.classSet.getId(categoryName) if category == None: self.exampleStats.filter("undefined_class") self.exampleStats.endExample() continue tokenText = token.get("text").lower() # if "stem_gazetteer" in self.styles: # tokenText = PorterStemmer.stem(tokenText) # if ("exclude_gazetteer" in self.styles) and self.gazetteer and tokenText not in self.gazetteer: # features = {} # features[self.featureSet.getId("exclude_gazetteer")] = 1 # extra = {"xtype":"token","t":token.get("id"),"excluded":"True"} # if entityIds != None: # extra["goldIds"] = entityIds # #examples.append( (sentenceGraph.getSentenceId()+".x"+str(exampleIndex),category,features,extra) ) # ExampleUtils.appendExamples([(sentenceGraph.getSentenceId()+".x"+str(exampleIndex),category,features,extra)], outfile) # exampleIndex += 1 # continue # FEATURES features = {} if not self.styles["names"]: features[self.featureSet.getId(namedEntityCountFeature)] = 1 #for k,v in bagOfWords.iteritems(): # features[self.featureSet.getId(k)] = v # pre-calculate bow _features_ features.update(bowFeatures) # for j in range(len(sentenceGraph.tokens)): # text = "bow_" + sentenceGraph.tokens[j].get("text") # if j < i: # features[self.featureSet.getId("bf_" + text)] = 1 # elif j > i: # features[self.featureSet.getId("af_" + text)] = 1 # Main features text = token.get("text") features[self.featureSet.getId("txt_"+text)] = 1 features[self.featureSet.getId("POS_"+token.get("POS"))] = 1 stem = PorterStemmer.stem(text) features[self.featureSet.getId("stem_"+stem)] = 1 features[self.featureSet.getId("nonstem_"+text[len(stem):])] = 1 # Normalized versions of the string (if same as non-normalized, overlap without effect) normalizedText = text.replace("-","").replace("/","").replace(",","").replace("\\","").replace(" ","").lower() if normalizedText == "bound": # should be for all irregular verbs normalizedText = "bind" features[self.featureSet.getId("txt_"+normalizedText)] = 1 norStem = PorterStemmer.stem(normalizedText) features[self.featureSet.getId("stem_"+norStem)] = 1 features[self.featureSet.getId("nonstem_"+normalizedText[len(norStem):])] = 1 ## Subspan features #textLower = text.lower() #for i in range(1, len(textLower)): # features[self.featureSet.getId("subspanbegin"+str(i)+"_"+textLower[0:i])] = 1 # features[self.featureSet.getId("subspanend"+str(i)+"_"+textLower[-i:])] = 1 # Substring features for string in text.split("-"): stringLower = string.lower() features[self.featureSet.getId("substring_"+stringLower)] = 1 features[self.featureSet.getId("substringstem_"+PorterStemmer.stem(stringLower))] = 1 # Linear order features for index in [-3,-2,-1,1,2,3]: if i + index > 0 and i + index < len(sentenceGraph.tokens): self.buildLinearOrderFeatures(sentenceGraph, i + index, str(index), features) # Linear n-grams if self.styles["linear_ngrams"]: self.buildLinearNGram(max(0, i-1), i, sentenceGraph, features) self.buildLinearNGram(max(0, i-2), i, sentenceGraph, features) if self.styles["phospho"]: if text.find("hospho") != -1: features[self.featureSet.getId("phospho_found")] = 1 features[self.featureSet.getId("begin_"+text[0:2].lower())] = 1 features[self.featureSet.getId("begin_"+text[0:3].lower())] = 1 if self.styles["bb_features"]: if text.lower() in self.bacteriaTokens: features[self.featureSet.getId("lpsnBacToken")] = 1 # Content if i > 0 and text[0].isalpha() and text[0].isupper(): features[self.featureSet.getId("upper_case_start")] = 1 for j in range(len(text)): if j > 0 and text[j].isalpha() and text[j].isupper(): features[self.featureSet.getId("upper_case_middle")] = 1 # numbers and special characters if text[j].isdigit(): features[self.featureSet.getId("has_digits")] = 1 if j > 0 and text[j-1] == "-": features[self.featureSet.getId("has_hyphenated_digit")] = 1 elif text[j] == "-": features[self.featureSet.getId("has_hyphen")] = 1 elif text[j] == "/": features[self.featureSet.getId("has_fslash")] = 1 elif text[j] == "\\": features[self.featureSet.getId("has_bslash")] = 1 # duplets if j > 0: features[self.featureSet.getId("dt_"+text[j-1:j+1].lower())] = 1 # triplets if j > 1: features[self.featureSet.getId("tt_"+text[j-2:j+1].lower())] = 1 # quadruplets (don't work, slight decrease (0.5 pp) on f-score #if j > 2: # features[self.featureSet.getId("qt_"+text[j-3:j+1].lower())] = 1 # Attached edges (Hanging in and out edges) t1InEdges = self.inEdgesByToken[token] for edge in t1InEdges: edgeType = edge[2].get("type") features[self.featureSet.getId("t1HIn_"+edgeType)] = 1 features[self.featureSet.getId("t1HIn_"+edge[0].get("POS"))] = 1 features[self.featureSet.getId("t1HIn_"+edgeType+"_"+edge[0].get("POS"))] = 1 tokenText = sentenceGraph.getTokenText(edge[0]) features[self.featureSet.getId("t1HIn_"+tokenText)] = 1 features[self.featureSet.getId("t1HIn_"+edgeType+"_"+tokenText)] = 1 tokenStem = PorterStemmer.stem(tokenText) features[self.featureSet.getId("t1HIn_"+tokenStem)] = 1 features[self.featureSet.getId("t1HIn_"+edgeType+"_"+tokenStem)] = 1 features[self.featureSet.getId("t1HIn_"+norStem+"_"+edgeType+"_"+tokenStem)] = 1 t1OutEdges = self.outEdgesByToken[token] for edge in t1OutEdges: edgeType = edge[2].get("type") features[self.featureSet.getId("t1HOut_"+edgeType)] = 1 features[self.featureSet.getId("t1HOut_"+edge[1].get("POS"))] = 1 features[self.featureSet.getId("t1HOut_"+edgeType+"_"+edge[1].get("POS"))] = 1 tokenText = sentenceGraph.getTokenText(edge[1]) features[self.featureSet.getId("t1HOut_"+tokenText)] = 1 features[self.featureSet.getId("t1HOut_"+edgeType+"_"+tokenText)] = 1 tokenStem = PorterStemmer.stem(tokenText) features[self.featureSet.getId("t1HOut_"+tokenStem)] = 1 features[self.featureSet.getId("t1HOut_"+edgeType+"_"+tokenStem)] = 1 features[self.featureSet.getId("t1HOut_"+norStem+"_"+edgeType+"_"+tokenStem)] = 1 # REL features if self.styles["rel_features"]: self.relFeatureBuilder.setFeatureVector(features) self.relFeatureBuilder.buildAllFeatures(sentenceGraph.tokens, i) self.relFeatureBuilder.setFeatureVector(None) # DDI13 features if self.styles["ddi13_features"]: for index in range(len(normalizedText)): features[self.featureSet.getId("ddi13_fromstart" + str(index) + "_" + normalizedText[:index+1])] = 1 features[self.featureSet.getId("ddi13_fromend" + str(index) + "_" + normalizedText[index:])] = 1 if self.styles["drugbank_features"]: self.drugFeatureBuilder.setFeatureVector(features) self.drugFeatureBuilder.tag = "ddi_" self.drugFeatureBuilder.buildDrugFeatures(token) self.drugFeatureBuilder.setFeatureVector(None) #self.wordNetFeatureBuilder.getTokenFeatures("show", "VBP") #tokTxt = token.get("text") #tokPOS = token.get("POS") #wordNetFeatures = [] #wordNetFeatures = self.wordNetFeatureBuilder.getTokenFeatures(tokTxt, tokPOS) #self.wordNetFeatureBuilder.getTokenFeatures(tokTxt, tokPOS) if self.styles["wordnet"]: tokTxt = token.get("text") tokPOS = token.get("POS") wordNetFeatures = self.wordNetFeatureBuilder.getTokenFeatures(tokTxt, tokPOS) for wordNetFeature in wordNetFeatures: #print wordNetFeature, features[self.featureSet.getId("WN_"+wordNetFeature)] = 1 #print if self.styles["giuliano"]: self.giulianoFeatureBuilder.setFeatureVector(features) self.giulianoFeatureBuilder.buildTriggerFeatures(token, sentenceGraph) self.giulianoFeatureBuilder.setFeatureVector(None) extra = {"xtype":"token","t":token.get("id")} if self.styles["bb_features"]: extra["trigex"] = "bb" # Request trigger extension in ExampleWriter if self.styles["epi_merge_negated"]: extra["unmergeneg"] = "epi" # Request trigger type unmerging if entityIds != None: extra["goldIds"] = entityIds # The entities to which this example corresponds #examples.append( (sentenceGraph.getSentenceId()+".x"+str(exampleIndex),category,features,extra) ) # chains self.buildChains(token, sentenceGraph, features) if self.styles["pos_pairs"]: self.buildPOSPairs(token, namedEntityHeadTokens, features) example = (sentenceGraph.getSentenceId()+".x"+str(exampleIndex), category, features, extra) ExampleUtils.appendExamples([example], outfile) exampleIndex += 1 self.exampleStats.endExample() #return examples return exampleIndex
def buildExamplesFromGraph(self, sentenceGraph, outfile, goldGraph=None, structureAnalyzer=None): """ Build one example for each token of the sentence """ if sentenceGraph.sentenceElement.get("origId") in self.skiplist: print >> sys.stderr, "Skipping sentence", sentenceGraph.sentenceElement.get( "origId") return 0 #[] #examples = [] exampleIndex = 0 self.tokenFeatures = {} self.tokenFeatureWeights = {} # determine (manually or automatically) the setting for whether sentences with no given entities should be skipped buildForNameless = False if structureAnalyzer and not structureAnalyzer.hasGroupClass( "GIVEN", "ENTITY" ): # no given entities points to no separate NER program being used buildForNameless = True if self.styles["build_for_nameless"]: # manually force the setting buildForNameless = True if self.styles["skip_for_nameless"]: # manually force the setting buildForNameless = False # determine whether sentences with no given entities should be skipped namedEntityHeadTokens = [] if not self.styles["names"]: namedEntityCount = 0 for entity in sentenceGraph.entities: if entity.get( "given" ) == "True": # known data which can be used for features namedEntityCount += 1 namedEntityCountFeature = "nameCount_" + str(namedEntityCount) # NOTE!!! This will change the number of examples and omit # all triggers (positive and negative) from sentences which # have no NE:s, possibly giving a too-optimistic performance # value. Such sentences can still have triggers from intersentence # interactions, but as such events cannot be recovered anyway, # looking for these triggers would be pointless. if namedEntityCount == 0 and not buildForNameless: # no names, no need for triggers return 0 #[] if self.styles["pos_pairs"]: namedEntityHeadTokens = self.getNamedEntityHeadTokens( sentenceGraph) else: for key in sentenceGraph.tokenIsName.keys(): sentenceGraph.tokenIsName[key] = False bagOfWords = {} for token in sentenceGraph.tokens: text = "bow_" + token.get("text") if not bagOfWords.has_key(text): bagOfWords[text] = 0 bagOfWords[text] += 1 if sentenceGraph.tokenIsName[token]: text = "ne_" + text if not bagOfWords.has_key(text): bagOfWords[text] = 0 bagOfWords[text] += 1 bowFeatures = {} for k in sorted(bagOfWords.keys()): bowFeatures[self.featureSet.getId(k)] = bagOfWords[k] self.inEdgesByToken = {} self.outEdgesByToken = {} self.edgeSetByToken = {} for token in sentenceGraph.tokens: #inEdges = sentenceGraph.dependencyGraph.in_edges(token, data=True) #fixedInEdges = [] #for edge in inEdges: # fixedInEdges.append( (edge[0], edge[1], edge[2]["element"]) ) #inEdges = fixedInEdges inEdges = sentenceGraph.dependencyGraph.getInEdges(token) #inEdges.sort(compareDependencyEdgesById) self.inEdgesByToken[token] = inEdges #outEdges = sentenceGraph.dependencyGraph.out_edges(token, data=True) #fixedOutEdges = [] #for edge in outEdges: # fixedOutEdges.append( (edge[0], edge[1], edge[2]["element"]) ) #outEdges = fixedOutEdges outEdges = sentenceGraph.dependencyGraph.getOutEdges(token) #outEdges.sort(compareDependencyEdgesById) self.outEdgesByToken[token] = outEdges self.edgeSetByToken[token] = set(inEdges + outEdges) for i in range(len(sentenceGraph.tokens)): token = sentenceGraph.tokens[i] # CLASS if len(sentenceGraph.tokenIsEntityHead[token]) > 0: categoryName, entityIds = self.getMergedEntityType( sentenceGraph.tokenIsEntityHead[token]) else: categoryName, entityIds = "neg", None self.exampleStats.beginExample(categoryName) # Recognize only non-named entities (i.e. interaction words) if sentenceGraph.tokenIsName[token] and not self.styles[ "names"] and not self.styles["all_tokens"]: self.exampleStats.filter("name") self.exampleStats.endExample() continue # if "selftrain_limits" in self.styles: # # any predicted entity not part of the self-training set causes example to be rejected # filtered = False # for entity in sentenceGraph.tokenIsEntityHead[token]: # if entity.get("selftrain") == "False": # self.exampleStats.filter("selftrain_limits") # self.exampleStats.endExample() # filtered = True # break # if filtered: # continue # if "selftrain_group" in self.styles: # # any predicted entity not part of the self-training set causes example to be rejected # filtered = False # for entity in sentenceGraph.tokenIsEntityHead[token]: # if entity.get("selftraingroup") not in self.selfTrainGroups: # self.exampleStats.filter("selftrain_group") # self.exampleStats.endExample() # filtered = True # break # if filtered: # continue if self.styles["pos_only"] and categoryName == "neg": self.exampleStats.filter("pos_only") self.exampleStats.endExample() continue category = self.classSet.getId(categoryName) if category == None: self.exampleStats.filter("undefined_class") self.exampleStats.endExample() continue tokenText = token.get("text").lower() # if "stem_gazetteer" in self.styles: # tokenText = PorterStemmer.stem(tokenText) # if ("exclude_gazetteer" in self.styles) and self.gazetteer and tokenText not in self.gazetteer: # features = {} # features[self.featureSet.getId("exclude_gazetteer")] = 1 # extra = {"xtype":"token","t":token.get("id"),"excluded":"True"} # if entityIds != None: # extra["goldIds"] = entityIds # #examples.append( (sentenceGraph.getSentenceId()+".x"+str(exampleIndex),category,features,extra) ) # ExampleUtils.appendExamples([(sentenceGraph.getSentenceId()+".x"+str(exampleIndex),category,features,extra)], outfile) # exampleIndex += 1 # continue # FEATURES features = {} if not self.styles["names"]: features[self.featureSet.getId(namedEntityCountFeature)] = 1 #for k,v in bagOfWords.iteritems(): # features[self.featureSet.getId(k)] = v # pre-calculate bow _features_ features.update(bowFeatures) # for j in range(len(sentenceGraph.tokens)): # text = "bow_" + sentenceGraph.tokens[j].get("text") # if j < i: # features[self.featureSet.getId("bf_" + text)] = 1 # elif j > i: # features[self.featureSet.getId("af_" + text)] = 1 # Main features text = token.get("text") features[self.featureSet.getId("txt_" + text)] = 1 features[self.featureSet.getId("POS_" + token.get("POS"))] = 1 stem = PorterStemmer.stem(text) features[self.featureSet.getId("stem_" + stem)] = 1 features[self.featureSet.getId("nonstem_" + text[len(stem):])] = 1 # Normalized versions of the string (if same as non-normalized, overlap without effect) normalizedText = text.replace("-", "").replace("/", "").replace( ",", "").replace("\\", "").replace(" ", "").lower() if normalizedText == "bound": # should be for all irregular verbs normalizedText = "bind" features[self.featureSet.getId("txt_" + normalizedText)] = 1 norStem = PorterStemmer.stem(normalizedText) features[self.featureSet.getId("stem_" + norStem)] = 1 features[self.featureSet.getId("nonstem_" + normalizedText[len(norStem):])] = 1 ## Subspan features #textLower = text.lower() #for i in range(1, len(textLower)): # features[self.featureSet.getId("subspanbegin"+str(i)+"_"+textLower[0:i])] = 1 # features[self.featureSet.getId("subspanend"+str(i)+"_"+textLower[-i:])] = 1 # Substring features for string in text.split("-"): stringLower = string.lower() features[self.featureSet.getId("substring_" + stringLower)] = 1 features[self.featureSet.getId( "substringstem_" + PorterStemmer.stem(stringLower))] = 1 if not self.styles["no_context"]: # Linear order features for index in [-3, -2, -1, 1, 2, 3]: if i + index > 0 and i + index < len(sentenceGraph.tokens): self.buildLinearOrderFeatures(sentenceGraph, i + index, str(index), features) # Linear n-grams if self.styles["linear_ngrams"]: self.buildLinearNGram(max(0, i - 1), i, sentenceGraph, features) self.buildLinearNGram(max(0, i - 2), i, sentenceGraph, features) if self.styles["phospho"]: if text.find("hospho") != -1: features[self.featureSet.getId("phospho_found")] = 1 features[self.featureSet.getId("begin_" + text[0:2].lower())] = 1 features[self.featureSet.getId("begin_" + text[0:3].lower())] = 1 if self.styles["bb_features"]: if text.lower() in self.bacteriaTokens: features[self.featureSet.getId("lpsnBacToken")] = 1 # Content if i > 0 and text[0].isalpha() and text[0].isupper(): features[self.featureSet.getId("upper_case_start")] = 1 for j in range(len(text)): if j > 0 and text[j].isalpha() and text[j].isupper(): features[self.featureSet.getId("upper_case_middle")] = 1 # numbers and special characters if text[j].isdigit(): features[self.featureSet.getId("has_digits")] = 1 if j > 0 and text[j - 1] == "-": features[self.featureSet.getId( "has_hyphenated_digit")] = 1 elif text[j] == "-": features[self.featureSet.getId("has_hyphen")] = 1 elif text[j] == "/": features[self.featureSet.getId("has_fslash")] = 1 elif text[j] == "\\": features[self.featureSet.getId("has_bslash")] = 1 # duplets if j > 0: features[self.featureSet.getId("dt_" + text[j - 1:j + 1].lower())] = 1 # triplets if j > 1: features[self.featureSet.getId("tt_" + text[j - 2:j + 1].lower())] = 1 # quadruplets (don't work, slight decrease (0.5 pp) on f-score #if j > 2: # features[self.featureSet.getId("qt_"+text[j-3:j+1].lower())] = 1 # Attached edges (Hanging in and out edges) if not self.styles["no_context"]: t1InEdges = self.inEdgesByToken[token] for edge in t1InEdges: edgeType = edge[2].get("type") features[self.featureSet.getId("t1HIn_" + edgeType)] = 1 features[self.featureSet.getId("t1HIn_" + edge[0].get("POS"))] = 1 features[self.featureSet.getId("t1HIn_" + edgeType + "_" + edge[0].get("POS"))] = 1 tokenText = sentenceGraph.getTokenText(edge[0]) features[self.featureSet.getId("t1HIn_" + tokenText)] = 1 features[self.featureSet.getId("t1HIn_" + edgeType + "_" + tokenText)] = 1 tokenStem = PorterStemmer.stem(tokenText) features[self.featureSet.getId("t1HIn_" + tokenStem)] = 1 features[self.featureSet.getId("t1HIn_" + edgeType + "_" + tokenStem)] = 1 features[self.featureSet.getId("t1HIn_" + norStem + "_" + edgeType + "_" + tokenStem)] = 1 t1OutEdges = self.outEdgesByToken[token] for edge in t1OutEdges: edgeType = edge[2].get("type") features[self.featureSet.getId("t1HOut_" + edgeType)] = 1 features[self.featureSet.getId("t1HOut_" + edge[1].get("POS"))] = 1 features[self.featureSet.getId("t1HOut_" + edgeType + "_" + edge[1].get("POS"))] = 1 tokenText = sentenceGraph.getTokenText(edge[1]) features[self.featureSet.getId("t1HOut_" + tokenText)] = 1 features[self.featureSet.getId("t1HOut_" + edgeType + "_" + tokenText)] = 1 tokenStem = PorterStemmer.stem(tokenText) features[self.featureSet.getId("t1HOut_" + tokenStem)] = 1 features[self.featureSet.getId("t1HOut_" + edgeType + "_" + tokenStem)] = 1 features[self.featureSet.getId("t1HOut_" + norStem + "_" + edgeType + "_" + tokenStem)] = 1 # REL features if self.styles["rel_features"]: self.relFeatureBuilder.setFeatureVector(features) self.relFeatureBuilder.buildAllFeatures( sentenceGraph.tokens, i) self.relFeatureBuilder.setFeatureVector(None) # DDI13 features if self.styles["ddi13_features"]: for index in range(len(normalizedText)): features[self.featureSet.getId("ddi13_fromstart" + str(index) + "_" + normalizedText[:index + 1])] = 1 features[self.featureSet.getId("ddi13_fromend" + str(index) + "_" + normalizedText[index:])] = 1 if self.styles["drugbank_features"]: self.drugFeatureBuilder.setFeatureVector(features) self.drugFeatureBuilder.tag = "ddi_" self.drugFeatureBuilder.buildDrugFeatures(token) self.drugFeatureBuilder.setFeatureVector(None) #self.wordNetFeatureBuilder.getTokenFeatures("show", "VBP") #tokTxt = token.get("text") #tokPOS = token.get("POS") #wordNetFeatures = [] #wordNetFeatures = self.wordNetFeatureBuilder.getTokenFeatures(tokTxt, tokPOS) #self.wordNetFeatureBuilder.getTokenFeatures(tokTxt, tokPOS) if self.styles["wordnet"]: tokTxt = token.get("text") tokPOS = token.get("POS") wordNetFeatures = self.wordNetFeatureBuilder.getTokenFeatures( tokTxt, tokPOS) for wordNetFeature in wordNetFeatures: #print wordNetFeature, features[self.featureSet.getId("WN_" + wordNetFeature)] = 1 #print if self.styles["giuliano"]: self.giulianoFeatureBuilder.setFeatureVector(features) self.giulianoFeatureBuilder.buildTriggerFeatures( token, sentenceGraph) self.giulianoFeatureBuilder.setFeatureVector(None) if self.styles["ontobiotope_features"]: self.ontobiotopeFeatureBuilder.setFeatureVector(features) self.ontobiotopeFeatureBuilder.buildOBOFeaturesForToken(token) self.ontobiotopeFeatureBuilder.setFeatureVector(None) extra = {"xtype": "token", "t": token.get("id")} if self.styles["bb_features"]: extra[ "trigex"] = "bb" # Request trigger extension in ExampleWriter if self.styles["epi_merge_negated"]: extra["unmergeneg"] = "epi" # Request trigger type unmerging if entityIds != None: extra[ "goldIds"] = entityIds # The entities to which this example corresponds #examples.append( (sentenceGraph.getSentenceId()+".x"+str(exampleIndex),category,features,extra) ) if self.styles["bb_spans"]: for span in sentenceGraph.sentenceElement.iter("span"): if span.get("headOffset") != token.get("charOffset"): continue #if span.get("source") != "spec": # continue #print span.get("headOffset"), token.get("charOffset"), span.get("source"), token.get("id") features[self.featureSet.getId("span_found")] = 1 features[self.featureSet.getId( "span_count")] = 1 + features.get( self.featureSet.getId("span_count"), 0) features[self.featureSet.getId("span_identifier" + span.get("identifier"))] = 1 features[self.featureSet.getId("span_type" + span.get("type"))] = 1 features[self.featureSet.getId("span_category" + span.get("category"))] = 1 features[self.featureSet.getId("span_source" + span.get("source"))] = 1 if "define_offset" in extra: prevOffset = [ int(x) for x in extra["define_offset"].split("-") ] assert len(prevOffset) == 2 newOffset = [ int(x) for x in span.get("charOffset").split("-") ] assert len(newOffset) == 2 prevOffsetRange = abs(prevOffset[0] - prevOffset[1]) newOffsetRange = abs(newOffset[0] - newOffset[1]) if newOffsetRange > prevOffsetRange: extra["define_offset"] = span.get("charOffset") else: extra["define_offset"] = span.get("charOffset") features[self.featureSet.getId("span_count_" + str( features.get(self.featureSet.getId("span_count"), 0)))] = 1 # chains if not self.styles["no_context"]: self.buildChains(token, sentenceGraph, features) if self.styles["pos_pairs"]: self.buildPOSPairs(token, namedEntityHeadTokens, features) if self.styles["wordvector"]: self.wordVectorFeatureBuilder.setFeatureVector(features) self.wordVectorFeatureBuilder.buildFeatures(token) self.wordVectorFeatureBuilder.setFeatureVector(None) example = (sentenceGraph.getSentenceId() + ".x" + str(exampleIndex), category, features, extra) ExampleUtils.appendExamples([example], outfile) exampleIndex += 1 self.exampleStats.endExample() #return examples return exampleIndex
def stemTokens(self): for token in self.tokensById.values(): token.stem = stemmer.stem(token.text)
def buildExamplesFromGraph(self, sentenceGraph, outfile, goldGraph=None, structureAnalyzer=None): """ Build one example for each token of the sentence """ examples = [] exampleIndex = 0 self.tokenFeatures = {} if goldGraph != None: entityToGold = EvaluateInteractionXML.mapEntities( sentenceGraph.entities, goldGraph.entities) namedEntityCount = 0 entityCount = 0 for entity in sentenceGraph.entities: if entity.get( "given" ) == "True": # known data which can be used for features namedEntityCount += 1 else: # known data which can be used for features entityCount += 1 namedEntityCountFeature = "nameCount_" + str(namedEntityCount) entityCountFeature = "entityCount_" + str(entityCount) bagOfWords = {} for token in sentenceGraph.tokens: text = "bow_" + token.get("text") if not bagOfWords.has_key(text): bagOfWords[text] = 0 bagOfWords[text] += 1 if sentenceGraph.tokenIsName[token]: text = "ne_" + text if not bagOfWords.has_key(text): bagOfWords[text] = 0 bagOfWords[text] += 1 if len(sentenceGraph.tokenIsEntityHead) > 0: text = "ge_" + text if not bagOfWords.has_key(text): bagOfWords[text] = 0 bagOfWords[text] += 1 text = token.get("text") if self.styles["speculation_words"] and text in self.specWords: if not bagOfWords.has_key("spec_bow_" + text): bagOfWords["spec_bow_" + text] = 0 bagOfWords["spec_bow_" + text] += 1 bagOfWords["spec_sentence"] = 1 bowFeatures = {} for k, v in bagOfWords.iteritems(): bowFeatures[self.featureSet.getId(k)] = v self.inEdgesByToken = {} self.outEdgesByToken = {} self.edgeSetByToken = {} for token in sentenceGraph.tokens: inEdges = sentenceGraph.dependencyGraph.getInEdges(token) self.inEdgesByToken[token] = inEdges outEdges = sentenceGraph.dependencyGraph.getOutEdges(token) self.outEdgesByToken[token] = outEdges self.edgeSetByToken[token] = set(inEdges + outEdges) for entity in sentenceGraph.entities: #token = sentenceGraph.tokens[i] token = sentenceGraph.entityHeadTokenByEntity[entity] # Recognize only non-named entities (i.e. interaction words) if entity.get("given") == "True": continue # CLASS if self.styles["classification"] == "multiclass": task3Type = "multiclass" categoryName = "" if entity.get("negation") == "True": categoryName += "negation" if entity.get("speculation") == "True": if categoryName != "": categoryName += "---" categoryName += "speculation" if categoryName == "": categoryName = "neg" category = self.classSet.getId(categoryName) elif self.styles["classification"] == "speculation": task3Type = "speculation" if entity.get("speculation") == "True": category = self.classSet.getId("speculation") else: category = 1 if goldGraph != None: if len(entityToGold[entity]) > 0 and entityToGold[entity][ 0].get("speculation") == "True": category = self.classSet.getId("speculation") else: category = 1 categoryName = self.classSet.getName(category) elif self.styles["classification"] == "negation": task3Type = "negation" if entity.get("negation") == "True": category = self.classSet.getId("negation") else: category = 1 if goldGraph != None: if len(entityToGold[entity]) > 0 and entityToGold[entity][ 0].get("negation") == "True": category = self.classSet.getId("negation") else: category = 1 categoryName = self.classSet.getName(category) self.exampleStats.beginExample(categoryName) # FEATURES features = {} # ENTITY TYPE #entityType = self.classSet.getId(self.getMergedEntityType(entity)) #del self.classSet.Ids[self.getMergedEntityType(entity)] #IF LOCAL # There's a mistake here. The entityType should be the string, not # the id of the type. But there's also another issue. getMergedEntityType # expects a list, not an item. Therefore the type is always empty -> # types don't get used in classification. But this is the code used in # the publication, so it will now be published as is, and fixed in a later # release. # # Besides, using the classSet here generates an unneeded # additional class, that shows up in evaluations etc. However, to be # able to publish the exact models used for the publication experiments, # this can't be fixed so it breaks feature id consistency. Therefore I'll # now just remove the redundant class id from the classSet. #ENDIF #features[self.featureSet.getId(entityType)] = 1 features[self.featureSet.getId(namedEntityCountFeature)] = 1 features[self.featureSet.getId(entityCountFeature)] = 1 #for k,v in bagOfWords.iteritems(): # features[self.featureSet.getId(k)] = v # pre-calculate bow _features_ features.update(bowFeatures) # for j in range(len(sentenceGraph.tokens)): # text = "bow_" + sentenceGraph.tokens[j].get("text") # if j < i: # features[self.featureSet.getId("bf_" + text)] = 1 # elif j > i: # features[self.featureSet.getId("af_" + text)] = 1 # Main features text = token.get("text") features[self.featureSet.getId("txt_" + text)] = 1 features[self.featureSet.getId("POS_" + token.get("POS"))] = 1 stem = PorterStemmer.stem(text) features[self.featureSet.getId("stem_" + stem)] = 1 features[self.featureSet.getId("nonstem_" + text[len(stem):])] = 1 if self.styles["speculation_words"]: if text in self.specWords: features[self.featureSet.getId("ent_spec")] = 1 if stem in self.specWordStems: features[self.featureSet.getId("ent_spec_stem")] = 1 # Linear order features for i in range(len(sentenceGraph.tokens)): if token == sentenceGraph.tokens[i]: break for index in [-3, -2, -1, 1, 2, 3]: if i + index > 0 and i + index < len(sentenceGraph.tokens): self.buildLinearOrderFeatures(sentenceGraph, i + index, str(index), features) # Content if i > 0 and text[0].isalpha() and text[0].isupper(): features[self.featureSet.getId("upper_case_start")] = 1 for j in range(len(text)): if j > 0 and text[j].isalpha() and text[j].isupper(): features[self.featureSet.getId("upper_case_middle")] = 1 # numbers and special characters if text[j].isdigit(): features[self.featureSet.getId("has_digits")] = 1 if j > 0 and text[j - 1] == "-": features[self.featureSet.getId( "has_hyphenated_digit")] = 1 elif text[j] == "-": features[self.featureSet.getId("has_hyphen")] = 1 elif text[j] == "/": features[self.featureSet.getId("has_fslash")] = 1 elif text[j] == "\\": features[self.featureSet.getId("has_bslash")] = 1 # duplets if j > 0: features[self.featureSet.getId("dt_" + text[j - 1:j + 1].lower())] = 1 # triplets if j > 1: features[self.featureSet.getId("tt_" + text[j - 2:j + 1].lower())] = 1 # Attached edges (Hanging in and out edges) t1InEdges = self.inEdgesByToken[token] for edge in t1InEdges: edgeType = edge[2].get("type") features[self.featureSet.getId("t1HIn_" + edgeType)] = 1 features[self.featureSet.getId("t1HIn_" + edge[0].get("POS"))] = 1 features[self.featureSet.getId("t1HIn_" + edgeType + "_" + edge[0].get("POS"))] = 1 tokenText = sentenceGraph.getTokenText(edge[0]) features[self.featureSet.getId("t1HIn_" + tokenText)] = 1 features[self.featureSet.getId("t1HIn_" + edgeType + "_" + tokenText)] = 1 t1OutEdges = self.outEdgesByToken[token] for edge in t1OutEdges: edgeType = edge[2].get("type") features[self.featureSet.getId("t1HOut_" + edgeType)] = 1 features[self.featureSet.getId("t1HOut_" + edge[1].get("POS"))] = 1 features[self.featureSet.getId("t1HOut_" + edgeType + "_" + edge[1].get("POS"))] = 1 tokenText = sentenceGraph.getTokenText(edge[1]) features[self.featureSet.getId("t1HOut_" + tokenText)] = 1 features[self.featureSet.getId("t1HOut_" + edgeType + "_" + tokenText)] = 1 self.buildChains(token, sentenceGraph, features) extra = { "xtype": "task3", "t3type": task3Type, "t": token.get("id"), "entity": entity.get("id") } #examples.append( (sentenceGraph.getSentenceId()+".x"+str(exampleIndex),category,features,extra) ) example = (sentenceGraph.getSentenceId() + ".x" + str(exampleIndex), category, features, extra) ExampleUtils.appendExamples([example], outfile) exampleIndex += 1 self.exampleStats.endExample() #return examples return exampleIndex
def buildExamplesFromGraph(self, sentenceGraph, outfile, goldGraph=None, structureAnalyzer=None): """ Build one example for each token of the sentence """ examples = [] exampleIndex = 0 self.tokenFeatures = {} if goldGraph != None: entityToGold = EvaluateInteractionXML.mapEntities(sentenceGraph.entities, goldGraph.entities) namedEntityCount = 0 entityCount = 0 for entity in sentenceGraph.entities: if entity.get("given") == "True": # known data which can be used for features namedEntityCount += 1 else: # known data which can be used for features entityCount += 1 namedEntityCountFeature = "nameCount_" + str(namedEntityCount) entityCountFeature = "entityCount_" + str(entityCount) bagOfWords = {} for token in sentenceGraph.tokens: text = "bow_" + token.get("text") if not bagOfWords.has_key(text): bagOfWords[text] = 0 bagOfWords[text] += 1 if sentenceGraph.tokenIsName[token]: text = "ne_" + text if not bagOfWords.has_key(text): bagOfWords[text] = 0 bagOfWords[text] += 1 if len(sentenceGraph.tokenIsEntityHead) > 0: text = "ge_" + text if not bagOfWords.has_key(text): bagOfWords[text] = 0 bagOfWords[text] += 1 text = token.get("text") if self.styles["speculation_words"] and text in self.specWords: if not bagOfWords.has_key("spec_bow_"+text): bagOfWords["spec_bow_"+text] = 0 bagOfWords["spec_bow_"+text] += 1 bagOfWords["spec_sentence"] = 1 bowFeatures = {} for k,v in bagOfWords.iteritems(): bowFeatures[self.featureSet.getId(k)] = v self.inEdgesByToken = {} self.outEdgesByToken = {} self.edgeSetByToken = {} for token in sentenceGraph.tokens: inEdges = sentenceGraph.dependencyGraph.getInEdges(token) self.inEdgesByToken[token] = inEdges outEdges = sentenceGraph.dependencyGraph.getOutEdges(token) self.outEdgesByToken[token] = outEdges self.edgeSetByToken[token] = set(inEdges + outEdges) for entity in sentenceGraph.entities: #token = sentenceGraph.tokens[i] token = sentenceGraph.entityHeadTokenByEntity[entity] # Recognize only non-named entities (i.e. interaction words) if entity.get("given") == "True": continue # CLASS if self.styles["classification"] == "multiclass": task3Type = "multiclass" categoryName = "" if entity.get("negation") == "True": categoryName += "negation" if entity.get("speculation") == "True": if categoryName != "": categoryName += "---" categoryName += "speculation" if categoryName == "": categoryName = "neg" category = self.classSet.getId(categoryName) elif self.styles["classification"] == "speculation": task3Type = "speculation" if entity.get("speculation") == "True": category = self.classSet.getId("speculation") else: category = 1 if goldGraph != None: if len(entityToGold[entity]) > 0 and entityToGold[entity][0].get("speculation") == "True": category = self.classSet.getId("speculation") else: category = 1 categoryName = self.classSet.getName(category) elif self.styles["classification"] == "negation": task3Type = "negation" if entity.get("negation") == "True": category = self.classSet.getId("negation") else: category = 1 if goldGraph != None: if len(entityToGold[entity]) > 0 and entityToGold[entity][0].get("negation") == "True": category = self.classSet.getId("negation") else: category = 1 categoryName = self.classSet.getName(category) self.exampleStats.beginExample(categoryName) # FEATURES features = {} # ENTITY TYPE #entityType = self.classSet.getId(self.getMergedEntityType(entity)) #del self.classSet.Ids[self.getMergedEntityType(entity)] #IF LOCAL # There's a mistake here. The entityType should be the string, not # the id of the type. But there's also another issue. getMergedEntityType # expects a list, not an item. Therefore the type is always empty -> # types don't get used in classification. But this is the code used in # the publication, so it will now be published as is, and fixed in a later # release. # # Besides, using the classSet here generates an unneeded # additional class, that shows up in evaluations etc. However, to be # able to publish the exact models used for the publication experiments, # this can't be fixed so it breaks feature id consistency. Therefore I'll # now just remove the redundant class id from the classSet. #ENDIF #features[self.featureSet.getId(entityType)] = 1 features[self.featureSet.getId(namedEntityCountFeature)] = 1 features[self.featureSet.getId(entityCountFeature)] = 1 #for k,v in bagOfWords.iteritems(): # features[self.featureSet.getId(k)] = v # pre-calculate bow _features_ features.update(bowFeatures) # for j in range(len(sentenceGraph.tokens)): # text = "bow_" + sentenceGraph.tokens[j].get("text") # if j < i: # features[self.featureSet.getId("bf_" + text)] = 1 # elif j > i: # features[self.featureSet.getId("af_" + text)] = 1 # Main features text = token.get("text") features[self.featureSet.getId("txt_"+text)] = 1 features[self.featureSet.getId("POS_"+token.get("POS"))] = 1 stem = PorterStemmer.stem(text) features[self.featureSet.getId("stem_"+stem)] = 1 features[self.featureSet.getId("nonstem_"+text[len(stem):])] = 1 if self.styles["speculation_words"]: if text in self.specWords: features[self.featureSet.getId("ent_spec")] = 1 if stem in self.specWordStems: features[self.featureSet.getId("ent_spec_stem")] = 1 # Linear order features for i in range(len(sentenceGraph.tokens)): if token == sentenceGraph.tokens[i]: break for index in [-3,-2,-1,1,2,3]: if i + index > 0 and i + index < len(sentenceGraph.tokens): self.buildLinearOrderFeatures(sentenceGraph, i + index, str(index), features) # Content if i > 0 and text[0].isalpha() and text[0].isupper(): features[self.featureSet.getId("upper_case_start")] = 1 for j in range(len(text)): if j > 0 and text[j].isalpha() and text[j].isupper(): features[self.featureSet.getId("upper_case_middle")] = 1 # numbers and special characters if text[j].isdigit(): features[self.featureSet.getId("has_digits")] = 1 if j > 0 and text[j-1] == "-": features[self.featureSet.getId("has_hyphenated_digit")] = 1 elif text[j] == "-": features[self.featureSet.getId("has_hyphen")] = 1 elif text[j] == "/": features[self.featureSet.getId("has_fslash")] = 1 elif text[j] == "\\": features[self.featureSet.getId("has_bslash")] = 1 # duplets if j > 0: features[self.featureSet.getId("dt_"+text[j-1:j+1].lower())] = 1 # triplets if j > 1: features[self.featureSet.getId("tt_"+text[j-2:j+1].lower())] = 1 # Attached edges (Hanging in and out edges) t1InEdges = self.inEdgesByToken[token] for edge in t1InEdges: edgeType = edge[2].get("type") features[self.featureSet.getId("t1HIn_"+edgeType)] = 1 features[self.featureSet.getId("t1HIn_"+edge[0].get("POS"))] = 1 features[self.featureSet.getId("t1HIn_"+edgeType+"_"+edge[0].get("POS"))] = 1 tokenText = sentenceGraph.getTokenText(edge[0]) features[self.featureSet.getId("t1HIn_"+tokenText)] = 1 features[self.featureSet.getId("t1HIn_"+edgeType+"_"+tokenText)] = 1 t1OutEdges = self.outEdgesByToken[token] for edge in t1OutEdges: edgeType = edge[2].get("type") features[self.featureSet.getId("t1HOut_"+edgeType)] = 1 features[self.featureSet.getId("t1HOut_"+edge[1].get("POS"))] = 1 features[self.featureSet.getId("t1HOut_"+edgeType+"_"+edge[1].get("POS"))] = 1 tokenText = sentenceGraph.getTokenText(edge[1]) features[self.featureSet.getId("t1HOut_"+tokenText)] = 1 features[self.featureSet.getId("t1HOut_"+edgeType+"_"+tokenText)] = 1 self.buildChains(token, sentenceGraph, features) extra = {"xtype":"task3","t3type":task3Type,"t":token.get("id"),"entity":entity.get("id")} #examples.append( (sentenceGraph.getSentenceId()+".x"+str(exampleIndex),category,features,extra) ) example = (sentenceGraph.getSentenceId()+".x"+str(exampleIndex),category,features,extra) ExampleUtils.appendExamples([example], outfile) exampleIndex += 1 self.exampleStats.endExample() #return examples return exampleIndex
def buildFeatures(self, token, linear=True, chains=True): sentenceGraph = self.sentenceGraph tokenIndex = None for i in range(len(self.sentenceGraph.tokens)): if token == self.sentenceGraph.tokens[i]: tokenIndex = i break assert tokenIndex != None token = self.sentenceGraph.tokens[tokenIndex] # if not "names" in self.styles: self.setFeature(self.namedEntityCountFeature, 1) # self.features.update(self.bowFeatures) # Note! these do not get tagged # for j in range(len(sentenceGraph.tokens)): # text = "bow_" + sentenceGraph.tokens[j].get("text") # if j < i: # features[self.featureSet.getId("bf_" + text)] = 1 # elif j > i: # features[self.featureSet.getId("af_" + text)] = 1 # Main features text = token.get("text") self.setFeature("txt_" + text, 1) self.setFeature("POS_" + token.get("POS"), 1) stem = PorterStemmer.stem(text) self.setFeature("stem_" + stem, 1) self.setFeature("nonstem_" + text[len(stem) :], 1) # Linear order features if linear: for index in [-3, -2, -1, 1, 2, 3]: if i + index > 0 and i + index < len(sentenceGraph.tokens): self.buildLinearOrderFeatures(sentenceGraph, i + index, str(index)) # Content if i > 0 and text[0].isalpha() and text[0].isupper(): self.setFeature("upper_case_start", 1) for j in range(len(text)): if j > 0 and text[j].isalpha() and text[j].isupper(): self.setFeature("upper_case_middle", 1) # numbers and special characters if text[j].isdigit(): self.setFeature("has_digits", 1) if j > 0 and text[j - 1] == "-": self.setFeature("has_hyphenated_digit", 1) elif text[j] == "-": self.setFeature("has_hyphen", 1) elif text[j] == "/": self.setFeature("has_fslash", 1) elif text[j] == "\\": self.setFeature("has_bslash", 1) # duplets if j > 0: self.setFeature("dt_" + text[j - 1 : j + 1].lower(), 1) # triplets if j > 1: self.setFeature("tt_" + text[j - 2 : j + 1].lower(), 1) # chains if chains: self.buildChains(token, sentenceGraph)