Lemmatization of English words in sentences in XML format by Python<\/p>\n
Python 2.7, NLTK 3.0
\nThe input XML file look likes this:<\/p>\n
<item id=\"2\" asks-for=\"cause\" most-plausible-alternative=\"1\"> <\/sentences> import xml.etree.cElementTree as ET #library for XML processing<\/p>\n from nltk.tokenize import word_tokenize #library for word tokenize<\/p>\n from nltk.stem import WordNetLemmatizer #library for word lemmatize tree = ET.parse('input.xml') #parse the XML tree from input.xml for item_of_root in root: #for each item tree.write('output.xml') #ouput the lemmatized tree to file The ElementTree XML API – Python 2.7.12 Documentation<\/a><\/p>\n Installing NLTK Data<\/a><\/p>\n Dive Into NLTK, Part I: Getting Started with NLTK<\/a><\/p>\n Dive Into NLTK, Part II: Sentence Tokenize and Word Tokenize<\/a><\/p>\n
\n<?xml version=\"1.0\" encoding=\"UTF-8\"?>
\n<sentences version=\"1.0\">
\n<item id=\"1\" asks-for=\"cause\" most-plausible-alternative=\"1\">
\n<p>my body cast a shadow over the grass . <\/p>
\n<a1>the sun be rise . <\/a1>
\n<a2>the grass be cut . <\/a2>
\n<\/item><\/p>\n
\n<p>the woman tolerate the woman friend 's difficult behavior . <\/p>
\n<a1>the woman know the woman friend be go through a hard time . <\/a1>
\n<a2>the woman felt that the woman friend take advantage of her kindness . <\/a2>
\n<\/item>
\n...<\/p>\n
\n<\/code>
\n<\/p>\nPython Code<\/h3>\n
\n#This setting is only necessary for error about 'encoding utf-8'
\nimport sys
\nreload(sys)
\nsys.setdefaultencoding("utf-8")<\/p>\n
\nwordnet_lemmatizer = WordNetLemmatizer()<\/p>\n
\nroot = tree.getroot() #get root element of the tree<\/p>\n
\nfor sentence in item_of_root: #for each sentence in the item
\nwords = word_tokenize(sentence.text) #divide sentence to words
\nsentenceNew = "" #contatiner for new lemmatized sentence
\nfor word in words: #for each word in the sentence
\nlamWord = wordnet_lemmatizer.lemmatize(word, pos='v') #lemmatize the words
\nsentenceNew += lamWord + ' ' #put the lemmatized word to the contatiner
\nsentence.text = sentenceNew #store the new sentence to the tree<\/p>\n
\n<\/code>
\n <\/p>\nReference<\/h3>\n