I'm working with a kind of unique situation. I have words in Language1 that I've defined in English. I then took each English word, took its word vector from a pretrained GoogleNews w2v model, and average the vectors for every definition. The result, an example with a 3 dimension vector:
L1_words={
'word1': array([ 5.12695312e-02, -2.23388672e-02, -1.72851562e-01], dtype=float32),
'word2': array([ 5.09211312e-02, -2.67828571e-01, -1.49875201e-03], dtype=float32)
}
What I want to do is cluster (using K-means probably, but I'm open to other ideas) the keys of the dict by their numpy-array values.
I've done this before with standard w2v models, but the issue I'm having is that this is a dictionary. Is there another data set I can convert this to? I'm inclined to write it to a csv/make it into a pandas datafram and use Pandas or R to work on it like that, but I'm told that floats are problem when it comes to things requiring binary (as in: they lose information in unpredictable ways). I tried saving my dictionary to hdf5, but dictionaries are not supported.
Thanks in advance!
If I understand your question correctly, you want to cluster words according to their W2V representation, but you are saving it as dictionary representation. If that's the case, I don't think it is a unique situation at all. All you got to do is to convert the dictionary into a matrix and then perform clustering in the matrix. If you represent each line in the matrix as one word in your dictionary you should be able to reference the words back after clustering.
I couldn't test the code below, so it may not be completely functional, but the idea is the following:
from nltk.cluster import KMeansClusterer
import nltk
# make the matrix with the words
words = L1_words.keys()
X = []
for w in words:
X.append(L1_words[w])
# perform the clustering on the matrix
NUM_CLUSTERS=3
kclusterer = KMeansClusterer(NUM_CLUSTERS,distance=nltk.cluster.util.cosine_distance)
assigned_clusters = kclusterer.cluster(X, assign_clusters=True)
# print the cluster each word belongs
for i in range(len(X)):
print(words[i], assigned_clusters[i])
You can read more in details in this link.
Related
I'm trying to perform a simple task which requires iterations and interactions with specific vectors after loading it into gensim's Word2Vec.
Basically, given a txt file of the form:
t1 -0.11307 -0.63909 -0.35103 -0.17906 -0.12349
t2 0.54553 0.18002 -0.21666 -0.090257 -0.13754
t3 0.22159 -0.13781 -0.37934 0.39926 -0.25967
where t1 is the name of the vector and what follows are the vectors themselves. I load it in using the function vecs = KeyedVectors.load_word2vec_format(datapath(f), binary=False).
Now, I want to iterate through the vectors I have and make a calculation, take summing up all of the vectors as an example. If this was read in using with open(f), I know I can just use .split(' ') on it, but since this is now a KeyedVector object, I'm not sure what to do.
I've looked through the word2vec documentation, as well as used dir(KeyedVectors) but I'm still not sure if there is an attribute like KeyedVectors.vectors or something that allows me to perform this task.
Any tips/help/advice would be much appreciated!
There's a list of all words in the KeyedVectors object in its .index_to_key property. So one way to sum all the vectors would be to retrieve each by name in a list comprehension:
np.sum([vecs[key] for key in vecs.index_to_key], axis=0)
But, if all you really wanted to do is sum the vectors – and the keys (word tokens) aren't an important part of your calculation, the set of all the raw word-vectors is available in the .vectors property, as a numpy array with one vector per row. So you could also do:
np.sum(vecs.vectors, axis=0)
So far, I pre-process text data using numpy and build-in fuctions (such as keras tokenizer class, tf.keras.preprocessing.text.Tokenizer: https://keras.io/api/preprocessing/text/).
And there is were I got stuck:
Since I am trying to scale up my model and data set, I am experimenting with spark and spark nlp (https://nlp.johnsnowlabs.com/docs/en/annotators#tokenizer)... however, I couldn´t yet find a similar working tokenizer. The fitted tokenizer must be later available to transform validation/new data.
My output should represent each token as an unique integer value (starting from 1), something like:
[ 10,... , 64, 555]
[ 1,... , 264, 39]
[ 12,..., 1158, 1770]
Currently, I was able to use the Spark NLP-tokenizer to obtain tokenized words:
[okay,..., reason, still, not, get, background]
[picture,..., expand, fill, whole, excited]
[not, worry,..., happy, well, depend, on, situation]
Does anyone have a solution which doesn´t require to copy the data out of the spark environment?
UPDATE:
I created two CSVs to clarify my current issue. The first file was created thru a pre-processing pipeline: 1. cleaned_delim_text
After that, the delimited words should be "translated" to integer values and the sequence should be padded with zeros to the same length: 2. cleaned_tok_text
Please try below combination -
1. Use tokenizer to convert the statements into words and then
2.use word2vec
to compute distributed vector representation of those words
I have a large dataset containing a mix of words and short phrases, such as:
dataset = [
"car",
"red-car",
"lorry",
"broken lorry",
"truck owner",
"train",
...
]
I am trying to find a way to determine the most similar word from a short sentence, such as:
input = "I love my car that is red" # should map to "red-car"
input = "I purchased a new lorry" # should map to "lorry"
input = "I hate my redcar" # should map to "red-car"
input = "I will use my truck" # should map to "truck owner"
input = "Look at that yellow lorri" # should map to "lorry"
I have tried a number of approaches to this with no avail, including:
Vectoring the dataset and the input using TfidfVectorizer, then calculating the Cosine similarity of the vectorized input value against each individual, vectorized item value from the dataset.
The problem is, this only really works if the input contains the exact word(s) that are in the dataset - so for example, in the case where the input = "trai" then it would have a cosine value of 0, whereas I am trying to get it to map to the value "train" in the dataset.
The most obvious solution would be to perform a simple spell check, but that may not be a valid option, because I still want to choose the most similar result, even when the words are slightly different, i.e.:
input = "broke" # should map to "broken lorry" given the above dataset
If someone could suggest other potential approach I could try, that would be much appreciated.
As #Aaalok has suggested in the comments, one idea is to use a different distance/similarity function. Possible candidates include
Levenshtein distance (measures the number of changes to transform one string into the other)
N-gram similarity (measures the number of shared n-grams between both strings)
Another possibility is feature generation, i.e. enhancing the items in your dataset with additional strings. These could be n-grams, stems, or whatever suits your needs. For example, you could (automatically) expand red-car into
red-car red car
Paragraph vector or doc2vec should solve your problem. Provided you've enough and proper dataset. Of course, you'll have to do lot of tuning to get your results right. You could try gensim/deeplearning4j. But you may have to use some other methods to manage spelling mistakes.
When I train Doc2vec (using Gensim's Doc2vec in Python) on corpus of about 10k documents (each has few hundred words) and then infer document vectors using the same documents, they are not at all similar to the trained document vectors. I would expect they would be at least somewhat similar.
That is I do model.docvecs['some_doc_id'] and model.infer_vector(documents['some_doc_id']).
Cosine distances between trained and inferred vectors for few first documents:
0.38277733326
0.284007549286
0.286488652229
0.173178792
0.370117008686
0.275438070297
0.377647638321
0.171194493771
0.350615143776
0.311795353889
0.342757165432
As you can see, they are not really similar. If the similarity is so terrible even for documents used for training, I can't even begin to try to infer unseen documents.
Training configuration:
model = Doc2Vec(documents=documents, dm=1, size=100, window=6, alpha=0.1, workers=4,
seed=44, sample=1e-5, iter=15, hs=0, negative=8, dm_mean=1, min_alpha=0.01, min_count=2)
Inferring:
model.infer_vector(tokens, steps=20, alpha=0.025)
Note on the side: Documents are always preprocessed the same way (I checked that the same list of tokens goes into training and into inferring).
Also I played with parameters around a bit, too, and results were similar. So if your suggestion would be something like "try increasing or decreasing this or that training parameter", I've most likely tried it. Maybe I just didn't come across the 'correct' parameters though.
Thanks for any suggestions as to what can I do to make it work better.
EDIT: I am willing and able to use any other available Python implementation of paragraph vectors (doc2vec). It doesn't have to be this one. If you know of another that can achieve better results.
EDIT: Minimal working example
import fnmatch
import os
from scipy.spatial.distance import cosine
from gensim.models import Doc2Vec
from gensim.models.doc2vec import TaggedDocument
from keras.preprocessing.text import text_to_word_sequence
files = {}
folder = 'some path' # each file contains few regular sentences
for f in fnmatch.filter(os.listdir(folder), '*.sent'):
files[f] = open(folder + '/' + f, 'r', encoding="UTF-8").read()
documents = []
for k, v in files.items():
words = text_to_word_sequence(v, lower=True) # converts string to list of words, removes commas etc.
documents.append(TaggedDocument(tags=[k], words=words))
d2 = Doc2Vec(size=200, documents=documents)
for doc in documents:
trained = d2.docvecs[doc.tags[0]]
inferred = d2.infer_vector(doc.words, steps=50)
print(cosine(trained, inferred)) # cosine similarity from scipy
What is the type of your documents object, and are you sure that it is a multiply-iterable object, so that the model can do all of its 16 passes over the set of TaggedDocument-shaped text examples? That is, does iter(documents) always return a fresh iterator, with all items as TaggedDocument-shaped objects with the right list-of-words in words and list-of-tags in tags? (A common error is to supply a corpus that can be iterated over only once, and then ignoring any logged hints/warnings that no real training has happening. The inference/similarity results from such a model will be essentially random.)
Then for infer_vector(), does documents[tag] really return just the list-of-words it expects (not TaggedDocument or string)? (Users often supply strings, rather than lists-of-tokens, for training or inference words and get results that are just noise.)
Was there evaluation-guided reason for changing various defaults, either a little (window=6, negative=8) or a lot (alpha=0.1, min_count=2)? Such tweaks may not be a major factor in your problem, and there's nothing magical about the class defaults. But until you have the basics working, it's best to stick close to common configuration. (And then even after the basics are working, limit changes to those that can be demonstrated as better via a repeatable scoring process.)
Some report needing much higher steps values – 100 or more – to get better inference results, though that would be most crucial for very-small documents (of a handful to couple dozen words) rather than the few-hundred-words documents you describe.
A corpus of 10k documents is on the small side for Paragraph Vectors (Doc2Vec), but with your smallish vector-size (100) and larger number of iterations (15), it might be workable.
If you're still having problems, you should expand your question with more code showing how documents works, some suggestive example documents, and your cosine-similarity evaluation process – to see if there are any oversights at each of those steps.
I'm trying to solve a problem of sentence comparison using naive approach of summing up word vectors and comparing the results. My goal is to match people by interest, so the dataset consists of names and short sentences describing their hobbies. The batches are fairly small, few hundreds of people, so i wanted to give it a try before digging into doc2vec.
I prepare the data by cleaning it completely, removing stop words, tokenizing and lemmatizing. I use pre-trained model for word vectors which returns adequate results when finding similarities for some test words. Also tried summing up the sentence words to find similarities in the original model - the matches do make sense. The similarities would be around general sense of the phrase.
For sentence matching I'm trying the following: create an empty model
b = gs.models.Word2Vec(min_count=1, size=300, sample=0, hs=0)
Build vocab out of names (or person id's), no training
#first create vocab with an empty vector
test = [['test']]
b.build_vocab(test)
b.wv.syn0[b.wv.vocab['test'].index] = b.wv.syn0[b.wv.vocab['test'].index]*0
#populate vocab from an array
b.build_vocab([personIds], update=True)
Summ each sentence's word vectors and store the results into the model for a corresponding id
#sentences are pulled from pandas dataset df. 'a' is a pre-trained model i use to get vectors for each word
def summ(phrase, start_model):
'''
vector addition function
'''
#starting with a vector of 0's
sum_vec = start_model.word_vec("cat_NOUN")*0
for word in phrase:
sum_vec += start_model.word_vec(word)
return sum_vec
for i, row in df.iterrows():
try:
personId = row["ID"]
summVec = summ(df.iloc[i,1],a)
#updating syn0 for each name/id in vocabulary
b.wv.syn0[b.wv.vocab[personId].index] = summVec
except:
pass
I understand that i shouldn't be expecting much accuracy here, but the t-SNE print doesn't show any clustering whatsoever. Finding similarities method also fails to find matches (<0.2 similarity coefficient basically for everything). [
Wondering if anyone has an idea of where did i go wrong? Is my approach valid at all?
Your code, as shown, neither does any train() of word-vectors (using your local text), nor does it pre-load any vectors from elsewhere. So any vectors which do exist – created by the build_vocab() calls – will still just be in their randomly-initialized starting locations, and be useless for any semantic purposes.
Suggestions:
either (a) train your own vectors from your text, which makes sense if you have a good quantity of text; or (b) load vectors from elsewhere. But don't try to do both. (Or, in the case of the code above, neither.)
The update=True option for build_vocab() should be considered an expert, experimental option – only worth tinkering with if you've already had things working in simpler modes, and you're sure you need it and understand all the implications.
Normal use won't ever explicitly re-assign new values into the Word2Vec model's syn0 property - those are managed by the class's training routines, so you never need to zero them out or modify them. You should tally up your own text summary vectors, based on word-vectors, outside the model in your own data structures.