使用 word2vec 将单词分类为类别 [英] Using word2vec to classify words in categories
问题描述
背景
我有一些带有一些样本数据的向量,每个向量都有一个类别名称(地点、颜色、名称).
I have vectors with some sample data and each vector has a category name (Places,Colors,Names).
['john','jay','dan','nathan','bob'] -> 'Names'
['yellow', 'red','green'] -> 'Colors'
['tokyo','bejing','washington','mumbai'] -> 'Places'
我的目标是训练一个模型,该模型接受一个新的输入字符串并预测它属于哪个类别.例如,如果新输入是紫色",那么我应该能够将颜色"预测为正确的类别.如果新输入是卡尔加里",它应该将地点"预测为正确的类别.
My objective is to train a model that take a new input string and predict which category it belongs to. For example if a new input is "purple" then I should be able to predict 'Colors' as the correct category. If the new input is "Calgary" it should predict 'Places' as the correct category.
方法
我做了一些研究,发现了 Word2vec.该库具有我可以使用的相似性"和最相似性"功能.所以我想到的一种蛮力方法如下:
I did some research and came across Word2vec. This library has a "similarity" and "mostsimilarity" function which i can use. So one brute force approach I thought of is the following:
- 接受新的意见.
- 计算它与每个向量中每个词的相似度并取平均值.
例如,对于输入pink",我可以计算它与向量names"中单词的相似度,取平均值,然后对其他 2 个向量也这样做.给我最高相似度平均值的向量将是输入所属的正确向量.
So for instance for input "pink" I can calculate its similarity with words in vector "names" take a average and then do that for the other 2 vectors also. The vector that gives me the highest similarity average would be the correct vector for the input to belong to.
问题
鉴于我在 NLP 和机器学习方面的知识有限,我不确定这是否是最好的方法,因此我正在寻求有关解决问题的更好方法的帮助和建议.我愿意接受所有建议,也请指出我在机器学习和 NLP 领域的新手可能犯的任何错误.
Given my limited knowledge in NLP and machine learning I am not sure if that is the best approach and hence I am looking for help and suggestions on better approaches to solve my problem. I am open to all suggestions and also please point out any mistakes I may have made as I am new to machine learning and NLP world.
推荐答案
如果您正在寻找最简单/最快的解决方案,那么我建议您采用预训练的词嵌入(Word2Vec 或 GloVe)并构建一个简单的查询系统就在它之上.这些向量已经在一个庞大的语料库上进行了训练,并且可能包含对您的领域数据的足够好的近似.
If you're looking for the simplest / fastest solution then I'd suggest you take the pre-trained word embeddings (Word2Vec or GloVe) and just build a simple query system on top of it. The vectors have been trained on a huge corpus and are likely to contain good enough approximation to your domain data.
以下是我的解决方案:
import numpy as np
# Category -> words
data = {
'Names': ['john','jay','dan','nathan','bob'],
'Colors': ['yellow', 'red','green'],
'Places': ['tokyo','bejing','washington','mumbai'],
}
# Words -> category
categories = {word: key for key, words in data.items() for word in words}
# Load the whole embedding matrix
embeddings_index = {}
with open('glove.6B.100d.txt') as f:
for line in f:
values = line.split()
word = values[0]
embed = np.array(values[1:], dtype=np.float32)
embeddings_index[word] = embed
print('Loaded %s word vectors.' % len(embeddings_index))
# Embeddings for available words
data_embeddings = {key: value for key, value in embeddings_index.items() if key in categories.keys()}
# Processing the query
def process(query):
query_embed = embeddings_index[query]
scores = {}
for word, embed in data_embeddings.items():
category = categories[word]
dist = query_embed.dot(embed)
dist /= len(data[category])
scores[category] = scores.get(category, 0) + dist
return scores
# Testing
print(process('pink'))
print(process('frank'))
print(process('moscow'))
为了运行它,您必须从 此处(小心,800Mb!).运行时,它应该产生如下内容:
In order to run it, you'll have to download and unpack the pre-trained GloVe data from here (careful, 800Mb!). Upon running, it should produce something like this:
{'Colors': 24.655489603678387, 'Names': 5.058711671829224, 'Places': 0.90213905274868011}
{'Colors': 6.8597321510314941, 'Names': 15.570847320556641, 'Places': 3.5302454829216003}
{'Colors': 8.2919375101725254, 'Names': 4.58830726146698, 'Places': 14.7840416431427}
...看起来很合理.就是这样!如果你不需要这么大的模型,你可以根据他们的tf-idf 分数.请记住,模型大小仅取决于您拥有的数据和您可能希望查询的单词.
... which looks pretty reasonable. And that's it! If you don't need such a big model, you can filter the words in glove
according to their tf-idf score. Remember that the model size only depends on the data you have and words you might want to be able to query.
这篇关于使用 word2vec 将单词分类为类别的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持IT屋!