How do I adapt code to make CNN model compatible with a higher dimension word embedding?-CodePudding

I have been following an online tutorial on 1D CNN for text classification. I have got the model to work with a self trained word2vec embedding of 100 dimensions, but I want to see how the model would preform when given a higher dimensional word embedding.

I have tried downloading a 300 dimension word2vec model and adding the .txt file in the CNN model and changing any dimensions from a 100 to 300. The model runs but produces bad results, the accuracy is 'nan' and the loss is 0.000 for all epochs.

What would i have to change for the model to work with the 300 dimension word2vec model? Thanks i have added the code below:

# load doc into memory
def load_doc(filename):
    # open the file as read only
    file = open(filename, 'r')
    # read all text
    text = file.read()
    # close the file
    file.close()
    return text
 
# turn a doc into clean tokens
def clean_doc(doc, vocab):
    # split into tokens by white space
    tokens = doc.split()
    # remove punctuation from each token
    table = str.maketrans('', '', punctuation)
    tokens = [w.translate(table) for w in tokens]
    # filter out tokens not in vocab
    tokens = [w for w in tokens if w in vocab]
    tokens = ' '.join(tokens)
    return tokens
 
# load all docs in a directory
def process_docs(directory, vocab, is_trian):
    documents = list()
    # walk through all files in the folder
    for filename in listdir(directory):
        # skip any reviews in the test set
        if is_trian and filename.startswith('cv9'):
            continue
        if not is_trian and not filename.startswith('cv9'):
            continue
        # create the full path of the file to open
        path = directory   '/'   filename
        # load the doc
        doc = load_doc(path)
        # clean doc
        tokens = clean_doc(doc, vocab)
        # add to list
        documents.append(tokens)
    return documents
 
# load embedding as a dict
def load_embedding(filename):
    # load embedding into memory, skip first line
    file = open(filename,'r')
    lines = file.readlines()[1:]
    file.close()
    # create a map of words to vectors
    embedding = dict()
    for line in lines:
        parts = line.split()
        # key is string word, value is numpy array for vector
        embedding[parts[0]] = asarray(parts[1:], dtype='float32')
    return embedding
 
# create a weight matrix for the Embedding layer from a loaded embedding
def get_weight_matrix(embedding, vocab):
    # total vocabulary size plus 0 for unknown words
    vocab_size = len(vocab)   1
    # define weight matrix dimensions with all 0
    weight_matrix = zeros((vocab_size, 100))
    # step vocab, store vectors using the Tokenizer's integer mapping
    for word, i in vocab.items():
        weight_matrix[i] = embedding.get(word)
    return weight_matrix
 
# load the vocabulary
vocab_filename = 'vocab.txt'
vocab = load_doc(vocab_filename)
vocab = vocab.split()
vocab = set(vocab)
 
# load all training reviews
positive_docs = process_docs('txt_sentoken/pos', vocab, True)
negative_docs = process_docs('txt_sentoken/neg', vocab, True)
train_docs = negative_docs   positive_docs
 
# create the tokenizer
tokenizer = Tokenizer()
# fit the tokenizer on the documents
tokenizer.fit_on_texts(train_docs)
 
# sequence encode
encoded_docs = tokenizer.texts_to_sequences(train_docs)
# pad sequences
max_length = max([len(s.split()) for s in train_docs])
Xtrain = pad_sequences(encoded_docs, maxlen=max_length, padding='post')
# define training labels
ytrain = array([0 for _ in range(900)]   [1 for _ in range(900)])
 
# load all test reviews
positive_docs = process_docs('txt_sentoken/pos', vocab, False)
negative_docs = process_docs('txt_sentoken/neg', vocab, False)
test_docs = negative_docs   positive_docs
# sequence encode
encoded_docs = tokenizer.texts_to_sequences(test_docs)
# pad sequences
Xtest = pad_sequences(encoded_docs, maxlen=max_length, padding='post')
# define test labels
ytest = array([0 for _ in range(100)]   [1 for _ in range(100)])
 
# define vocabulary size (largest integer value)
vocab_size = len(tokenizer.word_index)   1
 
# load embedding from file
raw_embedding = load_embedding('embedding_word2vec.txt')
# get vectors in the right order
embedding_vectors = get_weight_matrix(raw_embedding, tokenizer.word_index)
# create the embedding layer
embedding_layer = Embedding(vocab_size, 100, weights=[embedding_vectors], input_length=max_length, trainable=False)
 
# define model
model = Sequential()
model.add(embedding_layer)
model.add(Conv1D(filters=128, kernel_size=5, activation='relu'))
model.add(MaxPooling1D(pool_size=2))
model.add(Flatten())
model.add(Dense(1, activation='sigmoid'))
print(model.summary())
# compile network
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
# fit network
model.fit(Xtrain, ytrain, epochs=10, verbose=2)
# evaluate
loss, acc = model.evaluate(Xtest, ytest, verbose=0)
print('Test Accuracy: %f' % (acc*100))

CodePudding user response：

If you are using 300-dimensional vectors you need to change two things in your code. This line:

weight_matrix = zeros((vocab_size, 100))

To:

weight_matrix = zeros((vocab_size, 300))

And this line:

embedding_layer = Embedding(vocab_size, 100, weights=[embedding_vectors], input_length=max_length, trainable=False)

embedding_layer = Embedding(vocab_size, 300, weights=[embedding_vectors], input_length=max_length, trainable=False)

That way, each integer representing a word will be mapped to its 300-dimensional word vector.

Update 1

If you download w2v from gensim:

import gensim.downloader as api

wv = api.load('word2vec-google-news-300')

This seems to work:

from string import punctuation
from os import listdir
from numpy import array
from numpy import asarray
from numpy import zeros
import numpy as np
from keras.preprocessing.text import Tokenizer
from keras.preprocessing.sequence import pad_sequences
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import Flatten
from keras.layers import Embedding
from keras.layers.convolutional import Conv1D
from keras.layers.convolutional import MaxPooling1D


# load doc into memory
def load_doc(filename):
    # open the file as read only
    file = open(filename, 'r')
    # read all text
    text = file.read()
    # close the file
    file.close()
    return text


# turn a doc into clean tokens
def clean_doc(doc, vocab):
    # split into tokens by white space
    tokens = doc.split()
    # remove punctuation from each token
    table = str.maketrans('', '', punctuation)
    tokens = [w.translate(table) for w in tokens]
    # filter out tokens not in vocab
    tokens = [w for w in tokens if w in vocab]
    tokens = ' '.join(tokens)
    return tokens


# load all docs in a directory
def process_docs(directory, vocab, is_trian):
    documents = list()
    # walk through all files in the folder
    for filename in listdir(directory):
        # skip any reviews in the test set
        if is_trian and filename.startswith('cv9'):
            continue
        if not is_trian and not filename.startswith('cv9'):
            continue
        # create the full path of the file to open
        path = directory   '/'   filename
        # load the doc
        doc = load_doc(path)
        # clean doc
        tokens = clean_doc(doc, vocab)
        # add to list
        documents.append(tokens)
    return documents


# load embedding as a dict
def load_embedding(filename):
    # load embedding into memory, skip first line
    file = open(filename, 'r')
    lines = file.readlines()[1:]
    file.close()
    # create a map of words to vectors
    embedding = dict()
    for line in lines:
        parts = line.split()
        # key is string word, value is numpy array for vector
        embedding[parts[0]] = asarray(parts[1:], dtype='float32')
    return embedding


# create a weight matrix for the Embedding layer from a loaded embedding
def get_weight_matrix(embedding, vocab):
    # total vocabulary size plus 0 for unknown words
    vocab_size = len(vocab)   1
    # define weight matrix dimensions with all 0
    weight_matrix = zeros((vocab_size, 300))
    # step vocab, store vectors using the Tokenizer's integer mapping
    for word, i in vocab.items():
      try:
          weight_matrix[i] = embedding[word]
      except KeyError:
          weight_matrix[i] = np.random.uniform(size=300)
    return weight_matrix

# load the vocabulary
vocab_filename = 'vocab.txt'
vocab = load_doc(vocab_filename)
vocab = vocab.split()
vocab = set(vocab)

# load all training reviews
positive_docs = process_docs('/content/txt_sentoken/pos', vocab, True)
negative_docs = process_docs('/content/txt_sentoken/neg', vocab, True)
train_docs = negative_docs   positive_docs

# create the tokenizer
tokenizer = Tokenizer()
# fit the tokenizer on the documents
tokenizer.fit_on_texts(train_docs)

# sequence encode
encoded_docs = tokenizer.texts_to_sequences(train_docs)
# pad sequences
max_length = max([len(s.split()) for s in train_docs])
Xtrain = pad_sequences(encoded_docs, maxlen=max_length, padding='post')
# define training labels
ytrain = array([0 for _ in range(900)]   [1 for _ in range(900)])

# load all test reviews
positive_docs = process_docs('/content/txt_sentoken/pos', vocab, False)
negative_docs = process_docs('/content/txt_sentoken/neg', vocab, False)
test_docs = negative_docs   positive_docs
# sequence encode
encoded_docs = tokenizer.texts_to_sequences(test_docs)
# pad sequences
Xtest = pad_sequences(encoded_docs, maxlen=max_length, padding='post')
# define test labels
ytest = array([0 for _ in range(100)]   [1 for _ in range(100)])

# define vocabulary size (largest integer value)
vocab_size = len(tokenizer.word_index)   1

# load embedding from file
# get vectors in the right order
embedding_vectors = get_weight_matrix(wv, tokenizer.word_index)
# create the embedding layer
embedding_layer = Embedding(vocab_size, 300, weights=[embedding_vectors], input_length=max_length, trainable=False)

# define model
model = Sequential()
model.add(embedding_layer)
model.add(Conv1D(filters=128, kernel_size=5, activation='relu'))
model.add(MaxPooling1D(pool_size=2))
model.add(Flatten())
model.add(Dense(1, activation='sigmoid'))
print(model.summary())
# compile network
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
# fit network
model.fit(Xtrain, ytrain, epochs=10, verbose=2)
# evaluate
loss, acc = model.evaluate(Xtest, ytest, verbose=0)
print('Test Accuracy: %f' % (acc * 100))