如何为句子列表创建 window/chunk？

Question

我有句子列表，我想创建 skipgram (window size = 3) 但我不要希望计数器跨越句子，因为它们都是不相关的。

所以，如果我有以下句子：

[["my name is John"] , ["This PC is black"]]

三胞胎将是：

[my name is]
[name is john]
[this PC is]
[PC is black]

最好的方法是什么？

Answer 1

这是一个简单的函数。

def skipgram(corpus, window_size = 3):
    sg = []
    for sent in corpus:
        sent = sent[0].split()
        if len(sent) <= window_size:
            sg.append(sent)
        else:
            for i in range(0, len(sent)-window_size+1):
                sg.append(sent[i: i+window_size])
    return sg

corpus = [["my name is John"] , ["This PC is black"]]
skipgram(corups)

Answer 2

试试这个！

from nltk import ngrams

def generate_ngrams(sentences,window_size =3):
    for sentence in sentences:
        yield from ngrams(sentence[0].split(), window_size)

sentences= [["my name is John"] , ["This PC is black"]]

for c in generate_ngrams(sentences,3):
    print (c)

#output:
('my', 'name', 'is')
('name', 'is', 'John')
('This', 'PC', 'is')
('PC', 'is', 'black')

Answer 3

你并不真的想要一个 skipgram 本身，但你想要一个按大小划分的块，试试这个：

from lazyme import per_chunk

tokens = "my name is John".split()
list(per_chunk(tokens, 2))

[输出]:

[('my', 'name'), ('is', 'John')]

如果你想要滚动 window，即 ngrams:

from lazyme import per_window

tokens = "my name is John".split()
list(per_window(tokens, 2))

[输出]:

[('my', 'name'), ('name', 'is'), ('is', 'John')]

类似地在 NLTK 中用于 ngrams：

from nltk import ngrams

tokens = "my name is John".split()
list(ngrams(tokens, 2))

[输出]:

[('my', 'name'), ('name', 'is'), ('is', 'John')]

如果你想要实际的 skipgrams，

from nltk import skipgrams

tokens = "my name is John".split()
list(skipgrams(tokens, n=2, k=1))

[输出]:

[('my', 'name'),
 ('my', 'is'),
 ('name', 'is'),
 ('name', 'John'),
 ('is', 'John')]

如何为句子列表创建 window/chunk？

How to create window/chunk for list of sentences?

python

nlp

nltk

n-gram

language-model