def tagRawSentence(self, rawLine, DICT, word_dict, pos_dict):
     line = initializeSentence(DICT, rawLine)
     sen = []
     wordTags = line.split()
     for i in range(len(wordTags)):
         fwObject = FWObject.getFWObject(wordTags, i)
         word, tag = getWordTag(wordTags[i])
         node = self.findFiredNode(fwObject)
         if node.depth > 0:
             current_dict = ct.get(word.lower(), word_dict, default=0)
             if current_dict == 0:
                 sen.append(
                     (0, ct.get(node.conclusion.lower(),
                                pos_dict,
                                default=0), 0))
             else:
                 sen.append(
                     (ct.get("index", current_dict),
                      ct.get(node.conclusion.lower(), pos_dict,
                             default=0), ct.get("domain", current_dict)))
         else:  # Fired at root, return initialized tag
             current_dict = ct.get(word.lower(), word_dict, default=0)
             if current_dict == 0:
                 sen.append((0, ct.get(tag.lower(), pos_dict), 0))
             else:
                 sen.append(
                     (ct.get("index", current_dict),
                      ct.get(tag.lower(), pos_dict,
                             default=0), ct.get("domain", current_dict)))
     return sen
    def tagRawSentenceHash(self, rawLine, DICT, word_dict):
        line = initializeSentence(DICT, rawLine)

        sen = []
        wordTags = line.split()

        for i in range(len(wordTags)):
            fwObject = FWObject.getFWObject(wordTags, i)
            word, tag = getWordTag(wordTags[i])
            node = self.findFiredNode(fwObject)

            #Only hash word once and block out-of-lexicon words
            word_hash = murmurhash3_32(word, seed=0)
            try:
                word_cat = ct.get(word_hash, word_dict)
            except:
                word_cat = 0
                word_hash = 0

#Format and return
            if node.depth > 0:
                sen.append((word_hash, murmurhash3_32(node.conclusion,
                                                      seed=0), word_cat))
            else:  # Fired at root, return initialized tag
                sen.append((word_hash, murmurhash3_32(tag, seed=0), word_cat))

        return sen
Ejemplo n.º 3
0
    def tagRawSentenceHash(self, rawLine, DICT, word_dict):
        line = initializeSentence(DICT, rawLine)

        sen = []
        wordTags = line.split()

        for i in range(len(wordTags)):
            fwObject = FWObject.getFWObject(wordTags, i)
            word, tag = getWordTag(wordTags[i])
            node = self.findFiredNode(fwObject)

            #Format and return tagged word
            if node.depth > 0:
                tag = node.conclusion

            #Hash word / tag
            word = word + "/" + tag
            tag_hash = murmurhash3_32(tag, seed=0)
            word_hash = murmurhash3_32(word, seed=0)

            #Get semantic category
            try:
                word_cat = word_dict[word_hash]

            except:
                word_cat = 0
                word_hash = 0

            #Add to list
            sen.append((word_hash, tag_hash, word_cat))

        return sen
Ejemplo n.º 4
0
	def tagRawSentenceHash(self, rawLine, DICT, word_dict):
		line = initializeSentence(DICT, rawLine)

		sen = []
		wordTags = line.split()

		for i in range(len(wordTags)):
			fwObject = FWObject.getFWObject(wordTags, i)
			word, tag = getWordTag(wordTags[i])
			node = self.findFiredNode(fwObject)
			
			#Format and return tagged word
			if node.depth > 0:
				tag = node.conclusion
	
			#Hash word / tag
			word = word + "/" + tag
			tag_hash = murmurhash3_32(tag, seed=0)
			word_hash = murmurhash3_32(word, seed=0)
			
			#Get semantic category
			try:
				word_cat = word_dict[word_hash]
				
			except:
				word_cat = 0
				word_hash = 0
			
			#Add to list
			sen.append((word_hash, tag_hash, word_cat))

		return sen
    def tagRawSentenceGenSim(self, DICT, rawLine):
        line = initializeSentence(DICT, rawLine)

        sen = []
        wordTags = line.split()

        for i in range(len(wordTags)):
            fwObject = FWObject.getFWObject(wordTags, i)
            word, tag = getWordTag(wordTags[i])
            node = self.findFiredNode(fwObject)
            if node.depth > 0:
                sen.append(word + "/" + node.conclusion)
            else:  # Fired at root, return initialized tag
                sen.append(word + "/" + tag)
        return sen
Ejemplo n.º 6
0
	def tagRawSentenceGenSim(self, DICT, rawLine):
		line = initializeSentence(DICT, rawLine)

		sen = []
		wordTags = line.split()

		for i in range(len(wordTags)):
			fwObject = FWObject.getFWObject(wordTags, i)
			word, tag = getWordTag(wordTags[i])
			node = self.findFiredNode(fwObject)
			if node.depth > 0:
				sen.append(word + "/" + node.conclusion)
			else:# Fired at root, return initialized tag
				sen.append(word + "/" + tag)
		return sen
Ejemplo n.º 7
0
	def tagRawSentence(self, rawLine, DICT, word_dict, pos_dict):
		line = initializeSentence(DICT, rawLine)
		sen = []
		wordTags = line.split()
		for i in range(len(wordTags)):
			fwObject = FWObject.getFWObject(wordTags, i)
			word, tag = getWordTag(wordTags[i])
			node = self.findFiredNode(fwObject)
			if node.depth > 0:
				current_dict = ct.get(word.lower(), word_dict, default = 0)
				if current_dict == 0:
					sen.append((0, ct.get(node.conclusion.lower(), pos_dict, default = 0), 0))
				else:
					sen.append((ct.get("index", current_dict), ct.get(node.conclusion.lower(), pos_dict, default = 0), ct.get("domain", current_dict)))
			else:# Fired at root, return initialized tag
				current_dict = ct.get(word.lower(), word_dict, default = 0)
				if current_dict == 0:
					sen.append((0, ct.get(tag.lower(), pos_dict), 0))
				else:
					sen.append((ct.get("index", current_dict), ct.get(tag.lower(), pos_dict, default = 0), ct.get("domain", current_dict)))
		return sen