为什么 spaCy 不像 Stanford CoreNLP 那样在标记化过程中保留词内连字符?

Why does spaCy not preserve intra-word-hyphens during tokenization like Stanford CoreNLP does?

SpaCy 版本:2.0.11

Python版本:3.6.5

OS: Ubuntu 16.04

我的句子样本:

Marketing-Representative- won't die in car accident.

Out-of-box implementation

预期代币:

["Marketing-Representative", "-", "wo", "n't", "die", "in", "car", "accident", "."]

["Out-of-box", "implementation"]

SpaCy 令牌(默认分词器):

["Marketing", "-", "Representative-", "wo", "n't", "die", "in", "car", "accident", "."]

["Out", "-", "of", "-", "box", "implementation"]

我尝试创建自定义分词器,但它不会处理 spaCy 使用 tokenizer_exceptions(下面的代码)处理的所有边缘情况:

import spacy
from spacy.tokenizer import Tokenizer
from spacy.util import compile_prefix_regex, compile_infix_regex, compile_suffix_regex
import re
nlp = spacy.load('en')
prefix_re = compile_prefix_regex(nlp.Defaults.prefixes)
suffix_re = compile_suffix_regex(nlp.Defaults.suffixes)
infix_re = re.compile(r'''[.\,\?\:\;\...\‘\’\`\“\”\"\'~]''')

def custom_tokenizer(nlp):
    return Tokenizer(nlp.vocab, prefix_search=prefix_re.search,
                                suffix_search=suffix_re.search,
                                infix_finditer=infix_re.finditer,
                                token_match=None)
nlp.tokenizer = custom_tokenizer(nlp)
doc = nlp("Marketing-Representative- won't die in car accident.")
for token in doc:
    print(token.text)

输出:

Marketing-Representative-
won
'
t
die
in
car
accident
.

我需要有人指导我以适当的方式进行此操作。

要么在上面的正则表达式中进行更改,要么使用任何其他方法,或者我什至尝试了 spaCy 的基于规则的匹配器,但无法创建规则来处理超过 2 个单词之间的连字符,例如"out-of-box" 以便可以创建匹配器以与 span.merge() 一起使用。

无论哪种方式,我都需要让包含单词内连字符的单词成为 Stanford CoreNLP 处理的单个标记。

虽然 spacey usage site 中没有记录,

看起来我们只需要为我们正在使用的 *fix 添加 regex,在本例中为中缀。

此外,我们似乎可以使用自定义 regex

扩展 nlp.Defaults.prefixes
infixes = nlp.Defaults.prefixes + (r"[./]", r"[-]~", r"(.'.)")

这会给你想要的结果。无需将默认设置为 prefixsuffix,因为我们不使用它们。

import spacy
from spacy.tokenizer import Tokenizer
from spacy.util import compile_prefix_regex, compile_infix_regex, compile_suffix_regex
import re

nlp = spacy.load('en')

infixes = nlp.Defaults.prefixes + (r"[./]", r"[-]~", r"(.'.)")

infix_re = spacy.util.compile_infix_regex(infixes)

def custom_tokenizer(nlp):
    return Tokenizer(nlp.vocab, infix_finditer=infix_re.finditer)

nlp.tokenizer = custom_tokenizer(nlp)

s1 = "Marketing-Representative- won't die in car accident."
s2 = "Out-of-box implementation"

for s in s1,s2:
    doc = nlp("{}".format(s))
    print([token.text for token in doc])

结果

$python3 /tmp/nlp.py  
['Marketing-Representative-', 'wo', "n't", 'die', 'in', 'car', 'accident', '.']  
['Out-of-box', 'implementation']  

您可能想要修复插件正则表达式,以使其对接近所应用正则表达式的其他类型的标记更加健壮。

我还想修改 spaCy 的分词器以更接近 CoreNLP 的语义。下面粘贴的是我想出的,它解决了这个线程中的连字符问题(包括尾随的连字符)和一些额外的修复。我不得不复制默认的中缀表达式并对它们进行修改,但能够简单地附加一个新的后缀表达式:


import spacy
from spacy.lang.char_classes import ALPHA, ALPHA_LOWER, ALPHA_UPPER
from spacy.lang.char_classes import CONCAT_QUOTES, LIST_ELLIPSES, LIST_ICONS

def initializeTokenizer(nlp):

    prefixes = nlp.Defaults.prefixes 
    
    infixes = (
        LIST_ELLIPSES
        + LIST_ICONS
        + [
            r'(?<=[0-9])[+\-\*^](?=[0-9-])',
            r'(?<=[{al}{q}])\.(?=[{au}{q}])'.format(
                al=ALPHA_LOWER, au=ALPHA_UPPER, q=CONCAT_QUOTES
            ),
            # REMOVE: commented out regex that splits on hyphens between letters:
            #r"(?<=[{a}])(?:{h})(?=[{a}])".format(a=ALPHA, h=HYPHENS),
            # EDIT: remove split on slash between letters, and add comma
            #r'(?<=[{a}0-9])[:<>=/](?=[{a}])'.format(a=ALPHA),
            r'(?<=[{a}0-9])[:<>=,](?=[{a}])'.format(a=ALPHA),
            # ADD: ampersand as an infix character except for dual upper FOO&FOO variant
            r'(?<=[{a}0-9])[&](?=[{al}0-9])'.format(a=ALPHA, al=ALPHA_LOWER),
            r'(?<=[{al}0-9])[&](?=[{a}0-9])'.format(a=ALPHA, al=ALPHA_LOWER),
        ]
    )

    # ADD: add suffix to split on trailing hyphen
    custom_suffixes = [r'[-]']
    suffixes = nlp.Defaults.suffixes
    suffixes = tuple(list(suffixes) + custom_suffixes)

    infix_re = spacy.util.compile_infix_regex(infixes)
    suffix_re = spacy.util.compile_suffix_regex(suffixes)

    nlp.tokenizer.suffix_search = suffix_re.search
    nlp.tokenizer.infix_finditer = infix_re.finditer