对于词形还原,spacy有一个lists of words:形容词,副词,动词......还有例外列表:adverbs_irreg ...对于普通的那些有一组rules
我们以“更广泛”这个词为例
因为它是一个形容词,所以词典化的规则应该从这个列表中取出:
ADJECTIVE_RULES = [
["er", ""],
["est", ""],
["er", "e"],
["est", "e"]
]
据我所知,这个过程将是这样的:
1)获取单词的POS标签,以了解它是名词,动词...... 2)如果没有应用其中一个规则,如果单词在不规则案例列表中被直接替换。
现在,如何决定用“呃” - >“e”而不是“呃” - >“”来获得“宽”而不是“wid”?
Here它可以测试。
让我们从类定义开始:https://github.com/explosion/spaCy/blob/develop/spacy/lemmatizer.py
它从初始化3个变量开始:
class Lemmatizer(object):
@classmethod
def load(cls, path, index=None, exc=None, rules=None):
return cls(index or {}, exc or {}, rules or {})
def __init__(self, index, exceptions, rules):
self.index = index
self.exc = exceptions
self.rules = rules
现在,看看self.exc
的英文,我们看到它指向https://github.com/explosion/spaCy/tree/develop/spacy/lang/en/lemmatizer/init.py,它从目录https://github.com/explosion/spaCy/tree/master/spacy/en/lemmatizer加载文件
很可能是因为声明字符串in-code比通过I / O流式传输字符串更快。
仔细观察,它们似乎都来自原始的普林斯顿WordNet https://wordnet.princeton.edu/man/wndb.5WN.html
规则
再看一下,https://github.com/explosion/spaCy/tree/develop/spacy/lang/en/lemmatizer/_lemma_rules.py的规则类似于_morphy
nltk
的https://github.com/nltk/nltk/blob/develop/nltk/corpus/reader/wordnet.py#L1749规则
这些规则最初来自Morphy
软件https://wordnet.princeton.edu/man/morphy.7WN.html
另外,spacy
包含了一些不是来自Princeton Morphy的标点规则:
PUNCT_RULES = [
["“", "\""],
["”", "\""],
["\u2018", "'"],
["\u2019", "'"]
]
例外
至于例外,它们存储在*_irreg.py
的spacy
文件中,看起来它们也来自普林斯顿Wordnet。
很明显,如果我们查看原始WordNet .exc
(排除)文件(例如https://github.com/extjwnl/extjwnl-data-wn21/blob/master/src/main/resources/net/sf/extjwnl/data/wordnet/wn21/adj.exc)的一些镜像,如果从wordnet
下载nltk
包,我们会看到它是相同的列表:
alvas@ubi:~/nltk_data/corpora/wordnet$ ls
adj.exc cntlist.rev data.noun index.adv index.verb noun.exc
adv.exc data.adj data.verb index.noun lexnames README
citation.bib data.adv index.adj index.sense LICENSE verb.exc
alvas@ubi:~/nltk_data/corpora/wordnet$ wc -l adj.exc
1490 adj.exc
指数
如果我们看看spacy
lemmatizer的index
,我们发现它也来自Wordnet,例如https://github.com/explosion/spaCy/tree/develop/spacy/lang/en/lemmatizer/_adjectives.py和nltk
中重新分发的wordnet副本:
alvas@ubi:~/nltk_data/corpora/wordnet$ head -n40 data.adj
1 This software and database is being provided to you, the LICENSEE, by
2 Princeton University under the following license. By obtaining, using
3 and/or copying this software and database, you agree that you have
4 read, understood, and will comply with these terms and conditions.:
5
6 Permission to use, copy, modify and distribute this software and
7 database and its documentation for any purpose and without fee or
8 royalty is hereby granted, provided that you agree to comply with
9 the following copyright notice and statements, including the disclaimer,
10 and that the same appear on ALL copies of the software, database and
11 documentation, including modifications that you make for internal
12 use or for distribution.
13
14 WordNet 3.0 Copyright 2006 by Princeton University. All rights reserved.
15
16 THIS SOFTWARE AND DATABASE IS PROVIDED "AS IS" AND PRINCETON
17 UNIVERSITY MAKES NO REPRESENTATIONS OR WARRANTIES, EXPRESS OR
18 IMPLIED. BY WAY OF EXAMPLE, BUT NOT LIMITATION, PRINCETON
19 UNIVERSITY MAKES NO REPRESENTATIONS OR WARRANTIES OF MERCHANT-
20 ABILITY OR FITNESS FOR ANY PARTICULAR PURPOSE OR THAT THE USE
21 OF THE LICENSED SOFTWARE, DATABASE OR DOCUMENTATION WILL NOT
22 INFRINGE ANY THIRD PARTY PATENTS, COPYRIGHTS, TRADEMARKS OR
23 OTHER RIGHTS.
24
25 The name of Princeton University or Princeton may not be used in
26 advertising or publicity pertaining to distribution of the software
27 and/or database. Title to copyright in this software, database and
28 any associated documentation shall at all times remain with
29 Princeton University and LICENSEE agrees to preserve same.
00001740 00 a 01 able 0 005 = 05200169 n 0000 = 05616246 n 0000 + 05616246 n 0101 + 05200169 n 0101 ! 00002098 a 0101 | (usually followed by `to') having the necessary means or skill or know-how or authority to do something; "able to swim"; "she was able to program her computer"; "we were at last able to buy a car"; "able to get a grant for the project"
00002098 00 a 01 unable 0 002 = 05200169 n 0000 ! 00001740 a 0101 | (usually followed by `to') not having the necessary means or skill or know-how; "unable to get to town without a car"; "unable to obtain funds"
00002312 00 a 02 abaxial 0 dorsal 4 002 ;c 06037666 n 0000 ! 00002527 a 0101 | facing away from the axis of an organ or organism; "the abaxial surface of a leaf is the underside or side facing away from the stem"
00002527 00 a 02 adaxial 0 ventral 4 002 ;c 06037666 n 0000 ! 00002312 a 0101 | nearest to or facing toward the axis of an organ or organism; "the upper side of a leaf is known as the adaxial surface"
00002730 00 a 01 acroscopic 0 002 ;c 06066555 n 0000 ! 00002843 a 0101 | facing or on the side toward the apex
00002843 00 a 01 basiscopic 0 002 ;c 06066555 n 0000 ! 00002730 a 0101 | facing or on the side toward the base
00002956 00 a 02 abducent 0 abducting 0 002 ;c 06080522 n 0000 ! 00003131 a 0101 | especially of muscles; drawing away from the midline of the body or from an adjacent part
00003131 00 a 03 adducent 0 adductive 0 adducting 0 003 ;c 06080522 n 0000 + 01449236 v 0201 ! 00002956 a 0101 | especially of muscles; bringing together or drawing toward the midline of the body or toward an adjacent part
00003356 00 a 01 nascent 0 005 + 07320302 n 0103 ! 00003939 a 0101 & 00003553 a 0000 & 00003700 a 0000 & 00003829 a 0000 | being born or beginning; "the nascent chicks"; "a nascent insurgency"
00003553 00 s 02 emergent 0 emerging 0 003 & 00003356 a 0000 + 02625016 v 0102 + 00050693 n 0101 | coming into existence; "an emergent republic"
00003700 00 s 01 dissilient 0 002 & 00003356 a 0000 + 07434782 n 0101 | bursting open with force, as do some ripe seed vessels
基于spacy
引理器使用的字典,例外和规则主要来自普林斯顿WordNet及其Morphy软件,我们可以继续看看spacy
如何使用索引和异常来应用规则的实际实现。
我们回到https://github.com/explosion/spaCy/blob/develop/spacy/lemmatizer.py
主要行动来自函数而不是Lemmatizer
类:
def lemmatize(string, index, exceptions, rules):
string = string.lower()
forms = []
# TODO: Is this correct? See discussion in Issue #435.
#if string in index:
# forms.append(string)
forms.extend(exceptions.get(string, []))
oov_forms = []
for old, new in rules:
if string.endswith(old):
form = string[:len(string) - len(old)] + new
if not form:
pass
elif form in index or not form.isalpha():
forms.append(form)
else:
oov_forms.append(form)
if not forms:
forms.extend(oov_forms)
if not forms:
forms.append(string)
return set(forms)
lemmatize
method outside of the Lemmatizer
class?我不完全确定,但也许,确保可以在类实例之外调用词形还原函数但是考虑到@staticmethod
and @classmethod
存在,或许还有其他考虑因为函数和类已被解耦
比较spacy
lemmatize()函数与nltk中的morphy()
函数(最初来自http://blog.osteele.com/2004/04/pywordnet-20/十多年前创建的),morphy()
,Oliver Steele的WordNet形态Python端口的主要过程是:
对于spacy
,可能,它仍在开发中,鉴于TODO
在线https://github.com/explosion/spaCy/blob/develop/spacy/lemmatizer.py#L76
但一般过程似乎是:
在OOV处理方面,如果没有找到词形化形式,spacy返回原始字符串,在这方面,nltk
的morphy
实现也是如此,例如。
>>> from nltk.stem import WordNetLemmatizer
>>> wnl = WordNetLemmatizer()
>>> wnl.lemmatize('alvations')
'alvations'
可能另一个不同点是morphy
和spacy
如何决定分配给该单词的POS。在这方面,spacy
puts some linguistics rule in the Lemmatizer()
to decide whether a word is the base form and skips the lemmatization entirely if the word is already in the infinitive form (is_base_form()),如果要对语料库中的所有单词进行词形还原,并且相当一部分是不定式(已经是引理形式),这将节省相当多的时间。
但这在spacy
中是可能的,因为它允许引理器访问与某些形态规则紧密相关的POS。虽然对于morphy
虽然可以使用细粒度的PTB POS标签找出一些形态,但仍然需要花费一些精力来对它们进行排序以了解哪些形式是不定式的。
一般来说,形态特征的3个主要信号需要在POS标签中取消:
SpaCy在最初的答案(5月12日)之后确实对他们的lemmatizer进行了更改。我认为目的是在没有查找和规则处理的情况下使词典化更快。
因此,他们将词语预先解释并将它们保留在查找哈希表中,以便为他们预先词形化的词汇检索O(1)https://github.com/explosion/spaCy/blob/master/spacy/lang/en/lemmatizer/lookup.py
此外,为了统一语言的词典,这个词形变换器现在位于https://github.com/explosion/spaCy/blob/develop/spacy/lemmatizer.py#L92
但是上面讨论的底层词形还原步骤仍然与当前的spacy版本相关(4d2d7d586608ddc0bcb2857fb3c2d0d4c151ebfc
)
我想现在我们知道它适用于语言学规则和所有,另一个问题是“是否存在任何非基于规则的词形还原方法?”
但在回答之前的问题之前,“究竟什么是引理?”可能是更好的问题。
TLDR:spaCy检查它尝试生成的引理是否在已知的单词列表或该词性的异常中。
答案很长:
查看lemmatizer.py文件,特别是底部的lemmatize
函数。
def lemmatize(string, index, exceptions, rules):
string = string.lower()
forms = []
forms.extend(exceptions.get(string, []))
oov_forms = []
for old, new in rules:
if string.endswith(old):
form = string[:len(string) - len(old)] + new
if not form:
pass
elif form in index or not form.isalpha():
forms.append(form)
else:
oov_forms.append(form)
if not forms:
forms.extend(oov_forms)
if not forms:
forms.append(string)
return set(forms)
例如,对于英语形容词,它接受我们正在评估的字符串,已知形容词的index
,exceptions
和rules
,正如您所引用的,来自this directory(英语模型)。
在使字符串小写后我们在lemmatize
中做的第一件事是检查字符串是否在我们的已知异常列表中,其中包括诸如“更糟糕” - >“坏”之类的单词的引理规则。
然后我们通过我们的rules
并将每一个应用于字符串(如果适用)。对于wider
这个词,我们将应用以下规则:
["er", ""],
["est", ""],
["er", "e"],
["est", "e"]
我们将输出以下形式:["wid", "wide"]
。
然后,我们检查这个形式是否在我们的已知形容词的index
中。如果是,我们将其附加到表单中。否则,我们将它添加到oov_forms
,我猜这是词汇量的缩写。 wide
在索引中,因此它被添加。 wid
被添加到oov_forms
。
最后,我们返回一组找到的引理,或者匹配规则但不在我们的索引中的任何引理,或者只返回单词本身。
你上面发布的单词 - 引理链接适用于wider
,因为wide
在单词索引中。尝试类似He is blandier than I.
的东西spaCy会将blandier
(我组成的单词)标记为形容词,但它不在索引中,所以它只会将blandier
作为引理返回。
每种单词类型(形容词,名词,动词,副词)都有一套规则和一组单词。映射发生here:
INDEX = {
"adj": ADJECTIVES,
"adv": ADVERBS,
"noun": NOUNS,
"verb": VERBS
}
EXC = {
"adj": ADJECTIVES_IRREG,
"adv": ADVERBS_IRREG,
"noun": NOUNS_IRREG,
"verb": VERBS_IRREG
}
RULES = {
"adj": ADJECTIVE_RULES,
"noun": NOUN_RULES,
"verb": VERB_RULES,
"punct": PUNCT_RULES
}
然后在lemmatizer.py中的this line上正确的索引,规则和exc(excl我认为代表例外,例如不规则的例子)得到加载:
lemmas = lemmatize(string, self.index.get(univ_pos, {}),
self.exc.get(univ_pos, {}),
self.rules.get(univ_pos, []))
所有剩余的逻辑都在函数lemmatize中,并且令人惊讶地短。我们执行以下操作:
oov_forms
的单独列表中(这里我相信oov代表“词汇量不足”)