There are situations that we deal with short text, probably messy, without a lot of training data. In that case, we need external semantic information. Instead of using the conventional bag-of-words (BOW) model, we should employ word-embedding models, such as Word2Vec, GloVe etc.
Suppose we want to perform supervised learning, with three subjects, described by the following Python dictionary:
classdict={'mathematics': ['linear algebra',
'topology',
'algebra',
'calculus',
'variational calculus',
'functional field',
'real analysis',
'complex analysis',
'differential equation',
'statistics',
'statistical optimization',
'probability',
'stochastic calculus',
'numerical analysis',
'differential geometry'],
'physics': ['renormalization',
'classical mechanics',
'quantum mechanics',
'statistical mechanics',
'functional field',
'path integral',
'quantum field theory',
'electrodynamics',
'condensed matter',
'particle physics',
'topological solitons',
'astrophysics',
'spontaneous symmetry breaking',
'atomic molecular and optical physics',
'quantum chaos'],
'theology': ['divine providence',
'soteriology',
'anthropology',
'pneumatology',
'Christology',
'Holy Trinity',
'eschatology',
'scripture',
'ecclesiology',
'predestination',
'divine degree',
'creedal confessionalism',
'scholasticism',
'prayer',
'eucharist']}
And we implemented Word2Vec here. To add external information, we use a pre-trained Word2Vec model from Google, downloaded here. We can use it with Python package gensim. To load it, enter
from gensim.models import Word2Vec
wvmodel = Word2Vec.load_word2vec_format('<path-to>/GoogleNews-vectors-negative300.bin.gz', binary=True)
How do we represent a phrase in Word2Vec? How do we do the classification? Here I wrote two classes to do it.
Average
We can represent a sentence by summing the word-embedding representations of each word. The class, inside SumWord2VecClassification.py, is coded as follow:
from collections import defaultdict
import numpy as np
from nltk import word_tokenize
from scipy.spatial.distance import cosine
from utils import ModelNotTrainedException
class SumEmbeddedVecClassifier:
def __init__(self, wvmodel, classdict, vecsize=300):
self.wvmodel = wvmodel
self.classdict = classdict
self.vecsize = vecsize
self.trained = False
def train(self):
self.addvec = defaultdict(lambda : np.zeros(self.vecsize))
for classtype in self.classdict:
for shorttext in self.classdict[classtype]:
self.addvec[classtype] += self.shorttext_to_embedvec(shorttext)
self.addvec[classtype] /= np.linalg.norm(self.addvec[classtype])
self.addvec = dict(self.addvec)
self.trained = True
def shorttext_to_embedvec(self, shorttext):
vec = np.zeros(self.vecsize)
tokens = word_tokenize(shorttext)
for token in tokens:
if token in self.wvmodel:
vec += self.wvmodel[token]
norm = np.linalg.norm(vec)
if norm!=0:
vec /= np.linalg.norm(vec)
return vec
def score(self, shorttext):
if not self.trained:
raise ModelNotTrainedException()
vec = self.shorttext_to_embedvec(shorttext)
scoredict = {}
for classtype in self.addvec:
try:
scoredict[classtype] = 1 - cosine(vec, self.addvec[classtype])
except ValueError:
scoredict[classtype] = np.nan
return scoredict
Here the exception ModelNotTrainedException is just an exception raised if the model has not been trained yet, but scoring function was called by the user. (Codes listed in my Github repository.) The similarity will be calculated by cosine similarity.
Such an implementation is easy to understand and carry out. It is good enough for a lot of application. However, it has the problem that it does not take the relation between words or word order into account.
Convolutional Neural Network
To tackle the problem of word relations, we have to use deeper neural networks. Yoon Kim published a well cited paper regarding this in EMNLP in 2014, titled “Convolutional Neural Networks for Sentence Classification.” The model architecture is as follow: (taken from his paper)

Each word is represented by an embedded vector, but neighboring words are related through the convolutional matrix. And MaxPooling and a dense neural network were implemented afterwards. His paper involves multiple filters with variable window sizes / spatial extent, but for our cases of short phrases, I just use one window of size 2 (similar to dealing with bigram). While Kim implemented using Theano (see his Github repository), I implemented using keras with Theano backend. The codes, inside CNNEmbedVecClassification.py, are as follow:
import numpy as np
from keras.layers import Convolution1D, MaxPooling1D, Flatten, Dense
from keras.models import Sequential
from nltk import word_tokenize
from utils import ModelNotTrainedException
class CNNEmbeddedVecClassifier:
def __init__(self,
wvmodel,
classdict,
n_gram,
vecsize=300,
nb_filters=1200,
maxlen=15):
self.wvmodel = wvmodel
self.classdict = classdict
self.n_gram = n_gram
self.vecsize = vecsize
self.nb_filters = nb_filters
self.maxlen = maxlen
self.trained = False
def convert_trainingdata_matrix(self):
classlabels = self.classdict.keys()
lblidx_dict = dict(zip(classlabels, range(len(classlabels))))
# tokenize the words, and determine the word length
phrases = []
indices = []
for label in classlabels:
for shorttext in self.classdict[label]:
category_bucket = [0]*len(classlabels)
category_bucket[lblidx_dict[label]] = 1
indices.append(category_bucket)
phrases.append(word_tokenize(shorttext))
# store embedded vectors
train_embedvec = np.zeros(shape=(len(phrases), self.maxlen, self.vecsize))
for i in range(len(phrases)):
for j in range(min(self.maxlen, len(phrases[i]))):
train_embedvec[i, j] = self.word_to_embedvec(phrases[i][j])
indices = np.array(indices, dtype=np.int)
return classlabels, train_embedvec, indices
def train(self):
# convert classdict to training input vectors
self.classlabels, train_embedvec, indices = self.convert_trainingdata_matrix()
# build the deep neural network model
model = Sequential()
model.add(Convolution1D(nb_filter=self.nb_filters,
filter_length=self.n_gram,
border_mode='valid',
activation='relu',
input_shape=(self.maxlen, self.vecsize)))
model.add(MaxPooling1D(pool_length=self.maxlen-self.n_gram+1))
model.add(Flatten())
model.add(Dense(len(self.classlabels), activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='rmsprop')
# train the model
model.fit(train_embedvec, indices)
# flag switch
self.model = model
self.trained = True
def word_to_embedvec(self, word):
return self.wvmodel[word] if word in self.wvmodel else np.zeros(self.vecsize)
def shorttext_to_matrix(self, shorttext):
tokens = word_tokenize(shorttext)
matrix = np.zeros((self.maxlen, self.vecsize))
for i in range(min(self.maxlen, len(tokens))):
matrix[i] = self.word_to_embedvec(tokens[i])
return matrix
def score(self, shorttext):
if not self.trained:
raise ModelNotTrainedException()
# retrieve vector
matrix = np.array([self.shorttext_to_matrix(shorttext)])
# classification using the neural network
predictions = self.model.predict(matrix)
# wrangle output result
scoredict = {}
for idx, classlabel in zip(range(len(self.classlabels)), self.classlabels):
scoredict[classlabel] = predictions[0][idx]
return scoredict
The output is a vector of length equal to the number of class labels, 3 in our example. The elements of the output vector add up to one, indicating its score, and a nature of probability.
Evaluation
A simple cross-validation to the example data set does not tell a difference between the two algorithms:

However, we can test the algorithm with a few examples:
Example 1: “renormalization”
- Average: {‘mathematics’: 0.54135105096749336, ‘physics’: 0.63665460856632494, ‘theology’: 0.31014049736087901}
- CNN: {‘mathematics’: 0.093827009201049805, ‘physics’: 0.85451591014862061, ‘theology’: 0.051657050848007202}
As renormalization was a strong word in the training data, it gives an easy result. CNN can distinguish much more clearly.
Example 2: “salvation”
- Average: {‘mathematics’: 0.14939650156482298, ‘physics’: 0.21692765541184023, ‘theology’: 0.5698233329716329}
- CNN: {‘mathematics’: 0.012395491823554039, ‘physics’: 0.022725773975253105, ‘theology’: 0.96487873792648315}
“Salvation” is not found in the training data, but it is closely related to “soteriology,” which means the doctrine of salvation. So it correctly identifies it with theology.
Example 3: “coffee”
- Average: {‘mathematics’: 0.096820211601723272, ‘physics’: 0.081567332119268032, ‘theology’: 0.15962682945135631}
- CNN: {‘mathematics’: 0.27321341633796692, ‘physics’: 0.1950736939907074, ‘theology’: 0.53171288967132568}
Coffee is not related to all subjects. The first architecture correctly indicates the fact, but CNN, with its probabilistic nature, has to roughly equally distribute it (but not so well.)
The code can be found in my Github repository: stephenhky/PyShortTextCategorization. (This repository has been updated since this article was published. The link shows the version of the code when this appeared online.)
Continue reading “Short Text Categorization using Deep Neural Networks and Word-Embedding Models” →