17

件名に応じて感情を取得できるように、文の中で件名の抽出に取り組もうとしています。nltkこの目的のためにpython2.7で使用しています。次の文を例にとります。

Donald Trump is the worst president of USA, but Hillary is better than him

彼は私たちが見ることができるDonald TrumpとHillaryは2つの主題であり、関連する感情Donald Trumpは否定的ですが、関連する感情Hillaryは肯定的です. これまで、この文を名詞句のチャンクに分割することができ、次の結果を得ることができました。

(S
  (NP Donald/NNP Trump/NNP)
  is/VBZ
  (NP the/DT worst/JJS president/NN)
  in/IN
  (NP USA,/NNP)
  but/CC
  (NP Hillary/NNP)
  is/VBZ
  better/JJR
  than/IN
  (NP him/PRP))

では、これらの名詞句から主語を見つけるにはどうすればよいでしょうか。それでは、両方の主題を意味するフレーズをグループ化するにはどうすればよいでしょうか? 両方の主題を個別に意味するフレーズを取得したら、両方の感情分析を個別に実行できます。

編集

@Krzysiek ( spacy) が言及したライブラリを調べたところ、文中に依存関係ツリーも表示されました。

コードは次のとおりです。

from spacy.en import English
parser = English()

example = u"Donald Trump is the worst president of USA, but Hillary is better than him"
parsedEx = parser(example)
# shown as: original token, dependency tag, head word, left dependents, right dependents
for token in parsedEx:
    print(token.orth_, token.dep_, token.head.orth_, [t.orth_ for t in token.lefts], [t.orth_ for t in token.rights])

依存関係ツリーは次のとおりです。

(u'Donald', u'compound', u'Trump', [], [])
(u'Trump', u'nsubj', u'is', [u'Donald'], [])
(u'is', u'ROOT', u'is', [u'Trump'], [u'president', u',', u'but', u'is'])
(u'the', u'det', u'president', [], [])
(u'worst', u'amod', u'president', [], [])
(u'president', u'attr', u'is', [u'the', u'worst'], [u'of'])
(u'of', u'prep', u'president', [], [u'USA'])
(u'USA', u'pobj', u'of', [], [])
(u',', u'punct', u'is', [], [])
(u'but', u'cc', u'is', [], [])
(u'Hillary', u'nsubj', u'is', [], [])
(u'is', u'conj', u'is', [u'Hillary'], [u'better'])
(u'better', u'acomp', u'is', [], [u'than'])
(u'than', u'prep', u'better', [], [u'him'])
(u'him', u'pobj', u'than', [], [])

これにより、文のさまざまなトークンの依存関係に関する詳細な洞察が得られます。これは、異なるペア間の依存関係を説明する論文へのリンクです。このツリーを使用して、さまざまな主題の文脈上の単語をそれらに添付するにはどうすればよいですか?

4

2 に答える 2

17

私はスペーシーなライブラリをさらに調べていましたが、最終的に依存関係管理を通じて解決策を見つけました。このレポのおかげで、形容詞を主観的な動詞オブジェクト (SVAO にする) に含める方法と、クエリで複合主語を取り出す方法を理解しました。ここに私の解決策があります：

from nltk.stem.wordnet import WordNetLemmatizer
from spacy.lang.en import English

SUBJECTS = ["nsubj", "nsubjpass", "csubj", "csubjpass", "agent", "expl"]
OBJECTS = ["dobj", "dative", "attr", "oprd"]
ADJECTIVES = ["acomp", "advcl", "advmod", "amod", "appos", "nn", "nmod", "ccomp", "complm",
              "hmod", "infmod", "xcomp", "rcmod", "poss"," possessive"]
COMPOUNDS = ["compound"]
PREPOSITIONS = ["prep"]

def getSubsFromConjunctions(subs):
    moreSubs = []
    for sub in subs:
        # rights is a generator
        rights = list(sub.rights)
        rightDeps = {tok.lower_ for tok in rights}
        if "and" in rightDeps:
            moreSubs.extend([tok for tok in rights if tok.dep_ in SUBJECTS or tok.pos_ == "NOUN"])
            if len(moreSubs) > 0:
                moreSubs.extend(getSubsFromConjunctions(moreSubs))
    return moreSubs

def getObjsFromConjunctions(objs):
    moreObjs = []
    for obj in objs:
        # rights is a generator
        rights = list(obj.rights)
        rightDeps = {tok.lower_ for tok in rights}
        if "and" in rightDeps:
            moreObjs.extend([tok for tok in rights if tok.dep_ in OBJECTS or tok.pos_ == "NOUN"])
            if len(moreObjs) > 0:
                moreObjs.extend(getObjsFromConjunctions(moreObjs))
    return moreObjs

def getVerbsFromConjunctions(verbs):
    moreVerbs = []
    for verb in verbs:
        rightDeps = {tok.lower_ for tok in verb.rights}
        if "and" in rightDeps:
            moreVerbs.extend([tok for tok in verb.rights if tok.pos_ == "VERB"])
            if len(moreVerbs) > 0:
                moreVerbs.extend(getVerbsFromConjunctions(moreVerbs))
    return moreVerbs

def findSubs(tok):
    head = tok.head
    while head.pos_ != "VERB" and head.pos_ != "NOUN" and head.head != head:
        head = head.head
    if head.pos_ == "VERB":
        subs = [tok for tok in head.lefts if tok.dep_ == "SUB"]
        if len(subs) > 0:
            verbNegated = isNegated(head)
            subs.extend(getSubsFromConjunctions(subs))
            return subs, verbNegated
        elif head.head != head:
            return findSubs(head)
    elif head.pos_ == "NOUN":
        return [head], isNegated(tok)
    return [], False

def isNegated(tok):
    negations = {"no", "not", "n't", "never", "none"}
    for dep in list(tok.lefts) + list(tok.rights):
        if dep.lower_ in negations:
            return True
    return False

def findSVs(tokens):
    svs = []
    verbs = [tok for tok in tokens if tok.pos_ == "VERB"]
    for v in verbs:
        subs, verbNegated = getAllSubs(v)
        if len(subs) > 0:
            for sub in subs:
                svs.append((sub.orth_, "!" + v.orth_ if verbNegated else v.orth_))
    return svs

def getObjsFromPrepositions(deps):
    objs = []
    for dep in deps:
        if dep.pos_ == "ADP" and dep.dep_ == "prep":
            objs.extend([tok for tok in dep.rights if tok.dep_  in OBJECTS or (tok.pos_ == "PRON" and tok.lower_ == "me")])
    return objs

def getAdjectives(toks):
    toks_with_adjectives = []
    for tok in toks:
        adjs = [left for left in tok.lefts if left.dep_ in ADJECTIVES]
        adjs.append(tok)
        adjs.extend([right for right in tok.rights if tok.dep_ in ADJECTIVES])
        tok_with_adj = " ".join([adj.lower_ for adj in adjs])
        toks_with_adjectives.extend(adjs)

    return toks_with_adjectives

def getObjsFromAttrs(deps):
    for dep in deps:
        if dep.pos_ == "NOUN" and dep.dep_ == "attr":
            verbs = [tok for tok in dep.rights if tok.pos_ == "VERB"]
            if len(verbs) > 0:
                for v in verbs:
                    rights = list(v.rights)
                    objs = [tok for tok in rights if tok.dep_ in OBJECTS]
                    objs.extend(getObjsFromPrepositions(rights))
                    if len(objs) > 0:
                        return v, objs
    return None, None

def getObjFromXComp(deps):
    for dep in deps:
        if dep.pos_ == "VERB" and dep.dep_ == "xcomp":
            v = dep
            rights = list(v.rights)
            objs = [tok for tok in rights if tok.dep_ in OBJECTS]
            objs.extend(getObjsFromPrepositions(rights))
            if len(objs) > 0:
                return v, objs
    return None, None

def getAllSubs(v):
    verbNegated = isNegated(v)
    subs = [tok for tok in v.lefts if tok.dep_ in SUBJECTS and tok.pos_ != "DET"]
    if len(subs) > 0:
        subs.extend(getSubsFromConjunctions(subs))
    else:
        foundSubs, verbNegated = findSubs(v)
        subs.extend(foundSubs)
    return subs, verbNegated

def getAllObjs(v):
    # rights is a generator
    rights = list(v.rights)
    objs = [tok for tok in rights if tok.dep_ in OBJECTS]
    objs.extend(getObjsFromPrepositions(rights))

    potentialNewVerb, potentialNewObjs = getObjFromXComp(rights)
    if potentialNewVerb is not None and potentialNewObjs is not None and len(potentialNewObjs) > 0:
        objs.extend(potentialNewObjs)
        v = potentialNewVerb
    if len(objs) > 0:
        objs.extend(getObjsFromConjunctions(objs))
    return v, objs

def getAllObjsWithAdjectives(v):
    # rights is a generator
    rights = list(v.rights)
    objs = [tok for tok in rights if tok.dep_ in OBJECTS]

    if len(objs)== 0:
        objs = [tok for tok in rights if tok.dep_ in ADJECTIVES]

    objs.extend(getObjsFromPrepositions(rights))

    potentialNewVerb, potentialNewObjs = getObjFromXComp(rights)
    if potentialNewVerb is not None and potentialNewObjs is not None and len(potentialNewObjs) > 0:
        objs.extend(potentialNewObjs)
        v = potentialNewVerb
    if len(objs) > 0:
        objs.extend(getObjsFromConjunctions(objs))
    return v, objs

def findSVOs(tokens):
    svos = []
    verbs = [tok for tok in tokens if tok.pos_ == "VERB" and tok.dep_ != "aux"]
    for v in verbs:
        subs, verbNegated = getAllSubs(v)
        # hopefully there are subs, if not, don't examine this verb any longer
        if len(subs) > 0:
            v, objs = getAllObjs(v)
            for sub in subs:
                for obj in objs:
                    objNegated = isNegated(obj)
                    svos.append((sub.lower_, "!" + v.lower_ if verbNegated or objNegated else v.lower_, obj.lower_))
    return svos

def findSVAOs(tokens):
    svos = []
    verbs = [tok for tok in tokens if tok.pos_ == "VERB" and tok.dep_ != "aux"]
    for v in verbs:
        subs, verbNegated = getAllSubs(v)
        # hopefully there are subs, if not, don't examine this verb any longer
        if len(subs) > 0:
            v, objs = getAllObjsWithAdjectives(v)
            for sub in subs:
                for obj in objs:
                    objNegated = isNegated(obj)
                    obj_desc_tokens = generate_left_right_adjectives(obj)
                    sub_compound = generate_sub_compound(sub)
                    svos.append((" ".join(tok.lower_ for tok in sub_compound), "!" + v.lower_ if verbNegated or objNegated else v.lower_, " ".join(tok.lower_ for tok in obj_desc_tokens)))
    return svos

def generate_sub_compound(sub):
    sub_compunds = []
    for tok in sub.lefts:
        if tok.dep_ in COMPOUNDS:
            sub_compunds.extend(generate_sub_compound(tok))
    sub_compunds.append(sub)
    for tok in sub.rights:
        if tok.dep_ in COMPOUNDS:
            sub_compunds.extend(generate_sub_compound(tok))
    return sub_compunds

def generate_left_right_adjectives(obj):
    obj_desc_tokens = []
    for tok in obj.lefts:
        if tok.dep_ in ADJECTIVES:
            obj_desc_tokens.extend(generate_left_right_adjectives(tok))
    obj_desc_tokens.append(obj)

    for tok in obj.rights:
        if tok.dep_ in ADJECTIVES:
            obj_desc_tokens.extend(generate_left_right_adjectives(tok))

    return obj_desc_tokens

次のようなクエリを渡すと：

from spacy.lang.en import English
parser = English()

sentence = u"""
Donald Trump is the worst president of USA, but Hillary is better than him
"""

parse = parser(sentence)
print(findSVAOs(parse))

次のものが得られます。

[(u'donald trump', u'is', u'worst president'), (u'hillary', u'is', u'better')]

あなたのソリューションも@Krzysiekに感謝します。私は実際にあなたのライブラリを深く掘り下げて変更することができませんでした。問題を解決するために、上記のリンクを変更してみました。

于 2016-10-13T07:12:48.807 に答える
14

私は最近、非常によく似た問題を解決していました-件名、アクション、オブジェクトを抽出する必要がありました。そして、このライブラリを確認できるように、私の作品をオープン ソース化しました: https://github.com/krzysiekfonal/textpipeliner

これはスペイシー（nltkの反対）に基づいていますが、文ツリーにも基づいています。

たとえば、このドキュメントを例として spacy に埋め込んでみましょう:

import spacy
nlp = spacy.load("en")
doc = nlp(u"The Empire of Japan aimed to dominate Asia and the " \
               "Pacific and was already at war with the Republic of China " \
               "in 1937, but the world war is generally said to have begun on " \
               "1 September 1939 with the invasion of Poland by Germany and " \
               "subsequent declarations of war on Germany by France and the United Kingdom. " \
               "From late 1939 to early 1941, in a series of campaigns and treaties, Germany conquered " \
               "or controlled much of continental Europe, and formed the Axis alliance with Italy and Japan. " \
               "Under the Molotov-Ribbentrop Pact of August 1939, Germany and the Soviet Union partitioned and " \
               "annexed territories of their European neighbours, Poland, Finland, Romania and the Baltic states. " \
               "The war continued primarily between the European Axis powers and the coalition of the United Kingdom " \
               "and the British Commonwealth, with campaigns including the North Africa and East Africa campaigns, " \
               "the aerial Battle of Britain, the Blitz bombing campaign, the Balkan Campaign as well as the " \
               "long-running Battle of the Atlantic. In June 1941, the European Axis powers launched an invasion " \
               "of the Soviet Union, opening the largest land theatre of war in history, which trapped the major part " \
               "of the Axis' military forces into a war of attrition. In December 1941, Japan attacked " \
               "the United States and European territories in the Pacific Ocean, and quickly conquered much of " \
               "the Western Pacific.")

シンプルなパイプ構造を作成できるようになりました (パイプについては、このプロジェクトの readme を参照してください)。

pipes_structure = [SequencePipe([FindTokensPipe("VERB/nsubj/*"),
                                 NamedEntityFilterPipe(),
                                 NamedEntityExtractorPipe()]),
                   FindTokensPipe("VERB"),
                   AnyPipe([SequencePipe([FindTokensPipe("VBD/dobj/NNP"),
                                          AggregatePipe([NamedEntityFilterPipe("GPE"), 
                                                NamedEntityFilterPipe("PERSON")]),
                                          NamedEntityExtractorPipe()]),
                            SequencePipe([FindTokensPipe("VBD/**/*/pobj/NNP"),
                                          AggregatePipe([NamedEntityFilterPipe("LOC"), 
                                                NamedEntityFilterPipe("PERSON")]),
                                          NamedEntityExtractorPipe()])])]

engine = PipelineEngine(pipes_structure, Context(doc), [0,1,2])
engine.process()

その結果、次のようになります。

>>>[([Germany], [conquered], [Europe]),
 ([Japan], [attacked], [the, United, States])]

実際には、それは別のライブラリであるgrammaregexに強く基づいています(検索パイプ)。投稿からそれについて読むことができます: https://medium.com/@krzysiek89dev/grammaregex-library-regex-like-for-text-mining-49e5706c9c6d#.zgx7odhsc

編集済み

実際、readme で示した例では adj を破棄していますが、必要なのはエンジンに渡されるパイプ構造を必要に応じて調整することだけです。たとえば、サンプル文の場合、すべての文ごとに3つの要素（subj、verb、adj）のタプルを提供するような構造/ソリューションを提案できます。

import spacy
from textpipeliner import PipelineEngine, Context
from textpipeliner.pipes import *

pipes_structure = [SequencePipe([FindTokensPipe("VERB/nsubj/NNP"),
                                 NamedEntityFilterPipe(),
                                 NamedEntityExtractorPipe()]),
                       AggregatePipe([FindTokensPipe("VERB"),
                                      FindTokensPipe("VERB/xcomp/VERB/aux/*"),
                                      FindTokensPipe("VERB/xcomp/VERB")]),
                       AnyPipe([FindTokensPipe("VERB/[acomp,amod]/ADJ"),
                                AggregatePipe([FindTokensPipe("VERB/[dobj,attr]/NOUN/det/DET"),
                                               FindTokensPipe("VERB/[dobj,attr]/NOUN/[acomp,amod]/ADJ")])])
                      ]

engine = PipelineEngine(pipes_structure, Context(doc), [0,1,2])
engine.process()

それはあなたに結果を与えるでしょう：

[([Donald, Trump], [is], [the, worst])]

少し複雑なのは、複合文があり、lib が文ごとに 1 つのタプルを生成するという事実にあります。パイプ構造のリストをエンジンに渡して、より多くのタプルを生成できるようにする可能性をすぐに追加します (私のプロジェクトにも必要です)。文ごと。しかし、今のところ、構造が VERB ではなく VERB/conj/VERB のみ異なる複合送信用の 2 番目のエンジンを作成するだけで解決できます (これらの正規表現は常に ROOT から始まるため、VERB/conj/VERB は 2 番目の動詞につながります)。重文）：

pipes_structure_comp = [SequencePipe([FindTokensPipe("VERB/conj/VERB/nsubj/NNP"),
                                 NamedEntityFilterPipe(),
                                 NamedEntityExtractorPipe()]),
                   AggregatePipe([FindTokensPipe("VERB/conj/VERB"),
                                  FindTokensPipe("VERB/conj/VERB/xcomp/VERB/aux/*"),
                                  FindTokensPipe("VERB/conj/VERB/xcomp/VERB")]),
                   AnyPipe([FindTokensPipe("VERB/conj/VERB/[acomp,amod]/ADJ"),
                            AggregatePipe([FindTokensPipe("VERB/conj/VERB/[dobj,attr]/NOUN/det/DET"),
                                           FindTokensPipe("VERB/conj/VERB/[dobj,attr]/NOUN/[acomp,amod]/ADJ")])])
                  ]

engine2 = PipelineEngine(pipes_structure_comp, Context(doc), [0,1,2])

そして、両方のエンジンを実行すると、期待どおりの結果が得られます:)

engine.process()
engine2.process()
[([Donald, Trump], [is], [the, worst])]
[([Hillary], [is], [better])]

これが必要だと思います。もちろん、特定の例文のパイプ構造をすばやく作成しただけで、すべてのケースで機能するとは限りませんが、多くの文章構造を見たので、すでにかなりの割合を満たしていますが、FindTokensPipe などを追加するだけで済みます。現在うまくいかないケースと、いくつかの調整の後、非常に多くの可能な文をカバーできると確信しています（英語はそれほど複雑ではないので... :)

于 2016-09-29T07:42:41.893 に答える