Gushwell's Dev Notes

   Tweet

59. S式の解析
Stanford Core NLPの句構造解析の結果（S式）を読み込み，文中のすべての名詞句（NP）を表示せよ．入れ子になっている名詞句もすべて表示すること．

import copy

# 文字列をTokenに分解し、列挙する
class Tokenizer:
    def __init__(self, exp):
        self.exp = exp.replace('\n', '')
        self.curix = 0
        self.curr = ''
        self.prev = None
        self.gen = self.getTokens()

    def nextChar(self):
        if self.curix < len(self.exp):
            c = self.exp[self.curix]
            self.curix += 1
            return c
        return 0

    def getTokens(self):
        c = self.nextChar()
        token = ''
        while c != 0:
            if c == '(':
                yield c
            elif c == ')':
                if token != '':
                    yield token
                    token = ''
                yield c
            elif c == ' ':
                if token != '':
                    yield token
                    token = ''
            else:
                token += c
            c = self.nextChar()
        if token != '':
            yield token
        yield None

    def moveNext(self):
        if self.prev != None:
            r = copy.copy(self.prev)
            self.prev = None
            return r
        if self.curr != None:
            self.curr = next(self.gen)
        return self.curr

    # 一つ前に戻す （ただし連続しては呼び出せない)
    def movePrev(self):
        self.prev = self.curr

# Node.parseで利用するコンテキスストクラス
class Context:
    def __init__(self, exp):
        self.tokenizer = Tokenizer(exp)
        self.nplist = []

#<SExpression> :: ( <part>T <sentence> )
#<sentence> :: <word> | { ( <part> <sentence> ) }
#<part> :: ROOT | S | NP | VP | PP | ....

# <SExpression>を表すクラス
class NPExtractor:
    def parse(self, context):
        curr = context.tokenizer.moveNext()
        if curr == '(':
            # <part>を取り出す 取り出したpartは使わない
            context.tokenizer.moveNext()
            # <sentense>のパース
            node = Sentence()
            node.parse(context, False)
            # ) を取り出す
            curr = context.tokenizer.moveNext()
            if curr != ')':
                raise Exception
        else:
            raise Exception
        return ''

# <sentence>を表すクラス
class Sentence:
    def parse(self, context, isNp):
        phrase = []
        # 先読みする
        curr = context.tokenizer.moveNext()
        if curr != '(':
            # <word>の処理 読み取った単語を返す
            return curr
        # { ( <part> <sentence> )  の処理
        while curr == '(':
            # <part>を取り出す
            part = context.tokenizer.moveNext()
            # <sentense>のパース
            node = Sentence()
            w = node.parse(context, part == 'NP')
            # 現在の () の中の句はphraseに追加
            # ∵ (NP (JJ Many) (NNS challenges)) の Many challenges を記録する必要があるから
            phrase.append(w)
            if part == 'NP' and w != '':
                # 名詞句ならば、nplistにも記憶する
                # このpart が  (NP (JJ Many) (NNS challenges)) の NPならば、
                # w には、'Many challenges' が入っている
                context.nplist.append(w)
            # ) の処理
            curr = context.tokenizer.moveNext()
            if curr != ')':
                raise Exception
            # 次を取り出す
            curr = context.tokenizer.moveNext()
        # 先読みした分を戻す
        context.tokenizer.movePrev()
        if isNp:
            # parseが呼び出された時点で処理しているものがNPならば、phraseにある単語を連結し文字列化する
            # 先頭と最後の不要なものを取り除く かなり使わ伎だが...
            while phrase and (phrase[-1] == ',' or phrase[-1] == '' or phrase[-1] == '.'):
                phrase.pop()
            while phrase and (phrase[0] == ',' or phrase[0] == '' or phrase[0] == '.'):
                phrase.pop(0)
            return ' '.join(phrase)
        return ''

import re
from xml.etree import ElementTree
from NPExtractor import NPExtractor, Context

class NounPhrases:
    def __init__(self, filepath):
        xdoc = ElementTree.parse(filepath)
        root = xdoc.getroot()
        self.parses = root.findall('document/sentences/sentence/parse')

    def extract(self):
        with open('result59.txt', 'w', encoding='utf8') as w:
            for parse in self.parses:
                ctx = Context(parse.text)
                exp = NPExtractor()
                exp.parse(ctx)
                for p in ctx.nplist:
                    s = re.sub('-LRB-', '(', p)
                    s = re.sub('-RRB-',')', s)
                    w.write(s + '\n')

def main():
    nps = NounPhrases('nlp.txt.xml')
    nps.extract()

if __name__ == '__main__':
    main()

from NPExtractor import NPExtractor, Context

Natural language
processing
Natural language processing
Wikipedia
the free encyclopedia
Natural language processing
NLP
Natural language processing
a field
computer science
a field
artificial intelligence
linguistics
the interactions
computers
human ( natural ) languages
computers and human ( natural ) languages
the interactions
linguistics
a field , artificial intelligence , and linguistics
such
NLP
the area

Moore 's Law

the `` patient ''

general learning algorithms -

   Tweet

58. タプルの抽出
Stanford Core NLPの係り受け解析の結果（collapsed-dependencies）に基づき，「主語 述語 目的語」の組をタブ区切り形式で出力せよ．ただし，主語，述語，目的語の定義は以下を参考にせよ．
述語: nsubj関係とdobj関係の子（dependant）を持つ単語
主語: 述語からnsubj関係にある子（dependent）
目的語: 述語からdobj関係にある子（dependent）

<dep type="nsubj">
  <governor idx="13">enabling</governor>
  <dependent idx="8">understanding</dependent>
</dep>

<dep type="dobj">
  <governor idx="13">enabling</governor>
  <dependent idx="14">computers</dependent>
</dep>

述語: enabling
主語: understanding
目的語: computers

from xml.etree import ElementTree

class Dependency:
    def __init__(self, dep):
        self.type = dep.attrib['type']
        self.governor_ix = dep.find('governor').attrib['idx']
        self.governor_text = dep.find('governor').text
        self.dependent_ix = dep.find('dependent').attrib['idx']
        self.dependent_text = dep.find('dependent').text

class CollapsedDependencies:
    def __init__(self, filepath):
        xdoc = ElementTree.parse(filepath)
        root = xdoc.getroot()
        self.sentences = root.find('document/sentences')
        self.coreference = root.find('document/coreference')

    def enumCoreference(self):
        for e in self.coreference:
            yield e

    @staticmethod
    def toDot(deps):
        edges = []
        for dep in deps:
            governor = dep.find('governor')
            dependent = dep.find('dependent')
            if dependent.text != '.' and dependent.text != ',':
                edges.append((governor.text, dependent.text))
        return edges

    def getDependence(self, sentenceId):
        strid = str(sentenceId)
        sentences = self.sentences.find("sentence[@id='" + strid + "']")
        deps = sentences.find('dependencies[@type="collapsed-dependencies"]')
        return deps

    def enumDependencies(self):
        dependencies = self.sentences.findall('sentence/dependencies[@type="collapsed-dependencies"]')
        for deps in dependencies:
            yield deps

    @staticmethod
    def toDependencyList(deps):
        lst = []
        for dep in deps:
            lst.append(Dependency(dep))
        return lst


    def extractSVO(self, lst):
        subjs = self.findSubj(lst)
        for subj in subjs:
            objs = self.finObjs(lst, subj)
            for obj in objs:
                yield (subj.dependent_text, subj.governor_text, obj.dependent_text)

    @staticmethod
    def findSubj(lst):
        # subjの親が述語の可能性があるので、それを列挙
        return filter(lambda x: x.type == 'nsubj', lst)

    @staticmethod
    def finObjs(lst, subj):
        # subjと同じ親を持つノードを探す
        filterd = filter(lambda x: x.governor_ix == subj.governor_ix, lst)
        # その中からtypeが、dobjのものだけを取り出す
        return filter(lambda x: x.type == 'dobj', filterd)

def main():
    cd = CollapsedDependencies('chap06/nlp.txt.xml')
    with open('chap06/result58.txt', 'w', encoding='utf8') as w:
        for deps in cd.enumDependencies():
            nodes = cd.toDependencyList(deps)
            for s, v, o in cd.extractSVO(nodes):
                w.write('{}\t{}\t{}\n'.format(s, v, o))

    # このコメントアウトしてあるコードは、sentenceIdを指定して１文だけを処理するコード
    # sentenceId = 5
    # deps = cd.getDependence(sentenceId)
    # nodes = cd.toNodeList(deps)
    # print(sentenceId)
    # for s, v, o in cd.extractSVO(nodes):
    #     print(s.governor_text, v.governor_text, o.governor_text)
    # sentenceId += 1

if __name__ == '__main__':
    main()

understanding	enabling	computers
others	involve	generation
Turing	published	article
experiment	involved	translation
ELIZA	provided	interaction
patient	exceeded	base
ELIZA	provide	response
which	structured	information
underpinnings	discouraged	sort
that	underlies	approach
Some	produced	systems
which	make	decisions
systems	rely	which
that	contains	errors
implementations	involved	coding
algorithms	take	set
Some	produced	systems
which	make	decisions
models	have	advantage
they	express	certainty
Systems	have	advantages
Automatic	make	use
that	make	decisions

   Tweet

57. 係り受け解析
Stanford Core NLPの係り受け解析の結果（collapsed-dependencies）を有向グラフとして可視化せよ．可視化には，係り受け木をDOT言語に変換し，Graphvizを用いるとよい．また，Pythonから有向グラフを直接的に可視化するには，pydotを使うとよい．

 <dependencies type="collapsed-dependencies">
  <dep type="root">
    <governor idx="0">ROOT</governor>
    <dependent idx="2">language</dependent>
  </dep>
  <dep type="amod">
    <governor idx="2">language</governor>
    <dependent idx="1">Natural</dependent>
  </dep>
  <dep type="dep">
    <governor idx="2">language</governor>
    <dependent idx="3">processing</dependent>
  </dep>
  <dep type="punct">
    <governor idx="2">language</governor>
    <dependent idx="4">.</dependent>
  </dep>
</dependencies>

from xml.etree import ElementTree
import os
import pydot_ng as pydot

class CollapsedDependencies:
    def __init__(self, filepath):
        xdoc = ElementTree.parse(filepath)
        root = xdoc.getroot()
        self.sentences = root.find('document/sentences')
        self.coreference = root.find('document/coreference')

    def enumCoreference(self):
        for e in self.coreference:
            yield e

    @staticmethod
    def toDot(deps):
        edges = []
        for dep in deps:
            governor = dep.find('governor')
            dependent = dep.find('dependent')
            if dependent.text != '.' and dependent.text != ',':
                edges.append((governor.text, dependent.text))
        return edges

    def getDependence(self, sentenceId):
        strid = str(sentenceId)
        sentences = self.sentences.find("sentence[@id='" + strid + "']")
        deps = sentences.find('dependencies[@type="collapsed-dependencies"]')
        return self.toDot(deps)

    def enumDependencies(self):
        dependencies = self.sentences.findall('sentence/dependencies[@type="collapsed-dependencies"]')
        for deps in dependencies:
            yield self.toDot(deps)

    @staticmethod
    def toGraph(dot, filepath):
        os.environ["PATH"] += os.pathsep + 'C:/Program Files (x86)/Graphviz2.38/bin/'

        graph = pydot.Dot(graph_type='digraph')
        graph.set_node_defaults(fontname='Meiryo UI', fontsize='10')

        for s, t in dot:
            graph.add_edge(pydot.Edge(s, t))
        graph.write_png(filepath)

def main():
    cd = CollapsedDependencies('chap06/nlp.txt.xml')
    # sentenceId = 1
    # for dot in cd.enumDependencies():
    #     cd.toGraph(dot, "g57_{}.png".format(sentenceId))
    #     sentenceId += 1

    # ここでは、sentenceIdを指定して1文だけを処理するコードを実行
    sentenceId = 7
    dot = cd.getDependence(sentenceId)
    cd.toGraph(dot, "ag57_{}.png".format(sentenceId))

if __name__ == '__main__':
    main()

   Tweet

56. 共参照解析
Stanford Core NLPの共参照解析の結果に基づき，文中の参照表現（mention）を代表参照表現（representative mention）に置換せよ．ただし，置換するときは，「代表参照表現（参照表現）」のように，元の参照表現が分かるように配慮せよ．

java -cp "/Users/hideyuki/Documents/Dev/corenlp/*" -Xmx3g edu.stanford.nlp.pipeline.StanfordCoreNLP -annotators tokenize,ssplit,pos,lemma,ner,parse,dcoref -file nlp.txt

<coreference>
  <coreference>
    <mention representative="true">
      <sentence>3</sentence>
      <start>24</start>
      <end>25</end>
      <head>24</head>
      <text>computers</text>
    </mention>
    <mention>
      <sentence>5</sentence>
      <start>14</start>
      <end>15</end>
      <head>14</head>
      <text>computers</text>
    </mention>
  </coreference>
  ...

from xml.etree import ElementTree

class CoreferenceAnalyser:
    def __init__(self, filepath):
        xdoc = ElementTree.parse(filepath)
        root = xdoc.getroot()
        self.sentences = root.find('document/sentences')
        self.coreference = root.find('document/coreference')

    def enumCoreference(self):
        for e in self.coreference:
            yield e

    # mentionのtext内容をrepresentativeMentionの内容に置き換える
    def replaceMention(self, mention, representativeMention):
        sentenceid = mention.find('sentence').text
        startid = mention.find('start').text
        endid = str(int(mention.find('end').text) - 1)
        targetSentence = self.sentences.find("sentence[@id='" + sentenceid  + "']")
        startToken = targetSentence.find("tokens/token[@id='" + startid + "']")
        endToken = targetSentence.find("tokens/token[@id='" + endid + "']")

        text = representativeMention.find('text').text

        startword = startToken.find('word')
        startword.text = '「{}({}'.format(text, startword.text)
        endword = endToken.find('word')
        endword.text = endword.text + ')」'

    def replaceAll(self):
        for cf in self.enumCoreference():
            rm = cf.find("mention[@representative='true']")
            for m in cf.findall('mention'):
                if 'representative' in m.attrib:
                    continue
                self.replaceMention(m, rm)

    def writeText(self):
        with open('result56.txt', 'w', encoding='utf8') as w:
            prev = ''
            for e in self.sentences.findall('sentence/tokens/token'):
                word = e.find('word').text
                if word == '-LRB-':
                    word = '('
                elif word == '-RRB-':
                    word = ')'
                if word == '.':
                    w.write(word + '\n')
                elif word == ',' or word == '?' or word == '\'' or word == ')':
                    w.write(word)
                elif word == '(':
                    prev = word
                else:
                    if prev == '(':
                        w.write(' (' + word)
                    else:
                        w.write(' ' + word)
                    prev = ''

def main():
    ca = CoreferenceAnalyser('nlp.txt.xml')
    ca.replaceAll()
    ca.writeText()

if __name__ == '__main__':
    main()

 Natural language processing.
 From Wikipedia, the free encyclopedia.
 Natural language processing (NLP) is a field of computer science, artificial intelligence, and linguistics concerned with the interactions between computers and human (natural) languages.
 As such, NLP is related to the area of humani-computer interaction.
 Many challenges in NLP involve natural language understanding, that is, enabling 「computers(computers)」 to derive meaning from human or natural language input, and others involve natural language generation.
 History.
 The history of NLP generally starts in the 1950s, although work can be found from earlier periods.
 In 1950, Alan Turing published an article titled `` Computing Machinery and Intelligence '' which proposed what is now called the 「Alan Turing(Turing)」 test as a criterion of intelligence.
 The Georgetown experiment in 1954 involved fully automatic translation of more than sixty Russian sentences into English.
 The authors claimed that within three or five years, 「a solved problem(machine translation)」 would be a solved problem.
 However, real progress was much slower, and after the ALPAC report in 1966, which found that ten year long research had failed to fulfill the expectations, funding for machine translation was dramatically reduced.
 Little further research in 「a solved problem(machine translation)」 was conducted until the late 1980s, when the first statistical machine translation systems were developed.
 Some notably successful NLP systems developed in the 1960s were SHRDLU, 「SHRDLU(a natural language system working in restricted `` blocks worlds '' with restricted vocabularies)」, and ELIZA, a simulation of a Rogerian psychotherapist, written by Joseph Weizenbaum between 1964 to 1966.
 Using almost no information about human thought or emotion, ELIZA sometimes provided a startlingly human-like interaction.
 When the `` patient '' exceeded the very small knowledge base, 「ELIZA(ELIZA)」 might provide a generic response, for example, responding to `` 「the `` patient ''(My)」 head hurts '' with `` Why do you say 「you(「My head(your)」 head)」 hurts? ''.
 During the 1970s many programmers began to write ` conceptual ontologies', which structured real-world information into computer-understandable data.
 Examples are MARGIE (Schank, 1975), SAM (Cullingford, 1978), PAM (Wilensky, 「1978(1978)」), TaleSpin (Meehan, 1976), QUALM (Lehnert, 1977), Politics (Carbonell, 1979), and Plot Units (「Lehnert(Lehnert 1981)」).
 During this time, many chatterbots were written including PARRY, Racter, and Jabberwacky.
 Up to 「the late 1980s(the 1980s)」, most 「NLP(NLP)」 systems were based on complex sets of hand-written rules.
 Starting in 「the late 1980s(the late 1980s)」, however, there was a revolution in NLP with the introduction of machine learning algorithms for language processing.
 This was due to both the steady increase in computational power resulting from Moore 's Law and the gradual lessening of the dominance of Chomskyan theories of linguistics (e.g. transformational grammar), whose theoretical underpinnings discouraged the sort of corpus linguistics that underlies the machine-learning approach to 「language processing(language processing)」.
 Some of the earliest-used machine learning 「machine learning algorithms for language processing(algorithms)」, such as decision trees, produced systems of hard if-then rules similar to existing hand-written rules.
 However, Part of speech tagging introduced the use of Hidden Markov Models to 「NLP(NLP)」, and increasingly, research has focused on 「statistical models(statistical models, which make soft, probabilistic decisions based on attaching real-valued weights to the features making up the input data)」.
 The cache language models upon which many speech recognition systems now rely are 「The cache language models upon which many speech recognition systems now rely(examples of such statistical models)」.
 Such models are generally more robust when given unfamiliar input, especially 「as input(input that contains errors (as is very common for real-world data -RRB-)」, and produce more reliable results when integrated into a larger system comprising multiple subtasks.
 Many of the notable early successes occurred in the field of 「a solved problem(「a solved problem(machine translation)」, due especially to work at IBM Research, where successively more complicated statistical models were developed)」.
 「many speech recognition systems(These systems)」 were able to take 「the advantage(advantage of existing multilingual textual corpora that had been produced by the Parliament of Canada and the European Union as a result of laws calling for the translation of all governmental proceedings into all official languages of the corresponding systems of government)」.
 However, most other systems depended on corpora specifically developed for the tasks implemented by 「many speech recognition systems(these systems)」, which was (and often continues to be) a major limitation in the success of 「many speech recognition systems(these systems)」.
 As a result, a great deal of research has gone into methods of more effectively learning from limited amounts of data.
 Recent research has increasingly focused on unsupervised and semi-supervised learning algorithms.
 Such algorithms are able to learn from 「data(data that has not been hand-annotated with the desired answers)」, or using a combination of annotated and non-annotated data.
 Generally, this task is much more difficult than supervised learning, and typically produces less accurate results for a given amount of input data.
 However, there is an enormous amount of non-annotated data available (including, among other things, the entire content of the World Wide Web), which can often make up for the inferior results.
 NLP using machine learning.
 Modern NLP algorithms are based on 「machine learning(「machine learning(machine learning)」, especially statistical machine learning)」.
 The paradigm of 「machine learning(machine learning)」 is different from that of most prior attempts at 「language processing(language processing)」.
 Prior implementations of language-processing tasks typically involved the direct hand coding of large sets of 「hard if-then rules similar to existing hand-written rules(rules)」.
 The machine-learning paradigm calls instead for using general learning algorithms - often, although not always, grounded in statistical inference - to automatically learn such rules through the analysis of large corpora of typical real-world examples.
 A corpus (plural, 「existing multilingual textual corpora that had been produced by the Parliament of Canada and the European Union as a result of laws calling for the translation of all governmental proceedings into all official languages of the corresponding systems of government(`` corpora '')」) is 「A corpus -LRB- plural , `` corpora '' -RRB-(a set of documents (or sometimes, individual sentences) that have been hand-annotated with the correct values to be learned)」.
 Many different classes of 「machine learning algorithms for language processing(machine learning algorithms)」 have been applied to NLP tasks.
 「machine learning algorithms for language processing(These algorithms)」 take as input a large set of `` features '' that are generated from 「the input data(the input data)」.
 Some of the earliest-used algorithms, such as 「decision trees(decision trees)」, produced systems of hard if-then rules similar to the systems of 「hand-written rules(hand-written rules)」 that were then common.
 Increasingly, however, research has focused on 「statistical models(「statistical models(statistical models)」, which make 「soft , probabilistic decisions(soft, probabilistic decisions)」 based on attaching 「real-valued weights(real-valued weights)」 to each input feature)」.
 Such models have the advantage that 「Some of the earliest-used algorithms , such as decision trees(they)」 can express the relative certainty of many different possible answers rather than only one, producing more reliable results when such a model is included as a component of a larger system.
 Systems based on machine-learning algorithms have many advantages over hand-produced rules : The learning procedures used during 「machine learning(machine learning)」 automatically focus on the most common cases, whereas when writing 「hard if-then rules similar to existing hand-written rules(rules)」 by hand it is often not obvious at all where the effort should be directed.
 Automatic learning 「The learning procedures used during machine learning(procedures)」 can make use of statistical inference algorithms to produce models that are robust to unfamiliar input (e.g. containing words or structures that have not been seen before) and to erroneous input (e.g. with misspelled words or words accidentally omitted).
 Generally, handling such input gracefully with 「hand-written rules(hand-written rules)」 -- or more generally, creating systems of 「hand-written rules(hand-written rules)」 that make soft decisions -- extremely difficult, error-prone and time-consuming.
 Systems based on automatically learning the rules can be made more accurate simply by supplying more input data.
 However, 「the systems(systems based on 「hand-written rules(hand-written rules)」)」 can only be made more accurate by increasing the complexity of 「the rules(「the rules(the rules)」, which is a much more difficult task)」.
 In particular, there is a limit to the complexity of systems based on hand-crafted rules, beyond which the systems become more and more unmanageable.
 However, creating more data to input to 「Systems based on machine-learning algorithms(machine-learning systems)」 simply requires a corresponding increase in the number of man-hours worked, generally without significant increases in the complexity of the annotation process.
 The subfield of NLP devoted to learning approaches is known as Natural Language Learning (NLL) and 「Natural Language Learning -LRB- NLL -RRB-(its)」 conference CoNLL and peak body SIGNLL are sponsored by ACL, recognizing also their links with Computational Linguistics and Language Acquisition.
 When the aims of computational language learning research is to understand more about human language acquisition, or psycholinguistics, NLL overlaps into the related field of Computational Psycholinguistics.

   Tweet

55. 固有表現抽出
入力文中の人名をすべて抜き出せ．

<token id="4">
  <word>Alan</word>
  <lemma>Alan</lemma>
  <CharacterOffsetBegin>646</CharacterOffsetBegin>
  <CharacterOffsetEnd>650</CharacterOffsetEnd>
  <POS>NNP</POS>
  <NER>PERSON</NER>
  <Speaker>PER0</Speaker>
</token

from xml.etree import ElementTree

def getWords():
    xdoc = ElementTree.parse('nlp.txt.xml')
    root = xdoc.getroot()
    sentences = root.find('document/sentences')
    for e in sentences.findall('sentence/tokens/token'):
        if e.find('NER').text == 'PERSON':
            yield e.find('word')


def main():
    with open('result55.txt', 'w', encoding='utf8') as w:
        for word in getWords():
            w.write(f'{word.text}\n')


if __name__ == '__main__':
    main()

Alan
Turing
Joseph
Weizenbaum
MARGIE
Schank
Wilensky
Meehan
Lehnert
Carbonell
Lehnert
Racter
Jabberwacky
Moore

   Tweet

54. 品詞タグ付け
Stanford Core NLPの解析結果XMLを読み込み，単語，レンマ，品詞をタブ区切り形式で出力せよ．

import re
from xml.etree import ElementTree

def getWords():
    xdoc = ElementTree.parse('nlp.txt.xml')
    root = xdoc.getroot()
    sentences = root.find('document/sentences')
    for e in sentences.findall('sentence/tokens/token'):
        yield e.find('word'), e.find('lemma'), e.find('POS')

def main():
    with open('result54.txt', 'w', encoding='utf8') as w:
        for word, lemma, pos in getWords():
            m = re.search(r'[A-Z]', pos.text)
            if m:
                w.write(f'{word.text}\t{lemma.text}\t{pos.text}\n')


if __name__ == '__main__':
    main()

for e in sentences.findall('sentence/tokens/token'):
    yield e.find('word'), e.find('lemma'), e.find('POS')

    m = re.search(r'[A-Z]', pos.text)
    if m:
        w.write(f'{word.text}\t{lemma.text}\t{pos.text}\n')

Natural	natural	JJ
Natural	natural	JJ
language	language	NN
processing	processing	NN
From	from	IN
Wikipedia	Wikipedia	NNP
the	the	DT
free	free	JJ
encyclopedia	encyclopedia	NN
Natural	natural	JJ
language	language	NN
processing	processing	NN
-LRB-	-lrb-	-LRB-
NLP	nlp	NN
-RRB-	-rrb-	-RRB-
is	be	VBZ
a	a	DT
field	field	NN
of	of	IN
computer	computer	NN
science	science	NN
artificial	artificial	JJ
intelligence	intelligence	NN
and	and	CC
linguistics	linguistics	NNS
concerned	concern	VBN
with	with	IN
the	the	DT
interactions	interaction	NNS
between	between	IN
computers	computer	NNS