使用 Gensim 预训练的 GloVe 处理词汇表外的单词

Question

我正在处理一项 NLP 任务并加载了 Gensim 提供的 GloVe 向量：

import gensim.downloader
glove_vectors = gensim.downloader.load('glove-twitter-25')

我正在尝试获取句子中每个单词的单词嵌入，但其中一些不在词汇表中。

使用 Gensim API 处理它的最佳方法是什么？

谢谢！

Answer 1

加载model:

import gensim.downloader as api
model = api.load("glove-twitter-25")  # load glove vectors
# model.most_similar("cat")  # show words that similar to word 'cat'

有一种非常简单的方法可以找出模型词汇表中是否存在单词。

result = print('Word exists') if word in model.wv.vocab else print('Word does not exist")

除此之外，我还使用以下逻辑创建带有 N 个标记的句子嵌入（25 暗淡）：

from __future__ import print_function, division
import os
import re
import sys
import regex
import numpy as np
from functools import partial

from fuzzywuzzy import process
from Levenshtein import ratio as lev_ratio

import gensim
import tempfile


def vocab_check(model, word):
    similar_words = model.most_similar(word)
    match_ratio = 0.
    match_word = ''
    for sim_word, sim_score in similar_words:
        ratio = lev_ratio(word, sim_word)
        if ratio > match_ratio:
            match_word = sim_word
    if match_word == '':
        return similar_words[0][1]
    return model.similarity(word, match_word)


def sentence2vector(model, sent, dim=25):
    words = sent.split(' ')
    emb = [model[w.strip()] for w in words]
    weights = [1. if w in model.wv.vocab else vocab_check(model, w) for w in words]
    
    if len(emb) == 0:
        sent_vec = np.zeros(dim, dtype=np.float16)
    else:
        sent_vec = np.dot(weights, emb)

    sent_vec = sent_vec.astype("float16")
    return sent_vec