Core question : Right way(s) of using word-embeddings to represent text ?
I am building sentiment classification application for tweets. Classify tweets as - negative, neutral and positive.
I am doing this using Keras on top of theano and using word-embeddings (google's word2vec or Stanfords GloVe).
To represent tweet text I have done as follows:
used a pre-trained model (such as word2vec-twitter model) [M] to map words to their embeddings.
Use the words in the text to query M to get corresponding vectors. So if the tweet (T) is "Hello world" and M gives vectors V1 and V2 for the words 'Hello' and 'World'.
The tweet T can then be represented (V) as either V1+V2 (add vectors) or V1V2 (concatinate vectors)[These are 2 different strategies] [Concatenation means juxtaposition, so if V1, V2 are d-dimension vectors, in my example T is 2d dimension vector]
Then, the tweet T is represented by vector V.
If I follow the above, then My Dataset is nothing but vectors (which are sum or concatenation of word vectors depending on which strategy I use).
I am training a deepnet such as FFN, LSTM on this dataset. But my results arent coming out to be great.
Is this the right way to use word-embeddings to represent text ? What are the other better ways ?
Your feedback/critique will be of immense help.
I think that, for your purpose, it is better to think about another way of composing those vectors. The literature on word embeddings contains examples of criticisms to these kinds of composition (I will edit the answer with the correct references as soon as I find them).
I would suggest you to consider also other possible approaches, for instance:
Using the single word vectors as input to your net (I do not know your architecture, but the LSTM is recurrent so it can deal with sequences of words).
Using a full paragraph embedding (i.e. https://cs.stanford.edu/~quocle/paragraph_vector.pdf)
Summing them doesn't make any sense to be honest, because on summing them you get another vector which i don't think represents the semantics of "Hello World" or may be it does but it won't surely hold true for longer sentences in general
Instead it would be better to feed them as sequence as in that way it at least preserves sequence in meaningful way which seems to fit more to your problem.
e.g A hates apple Vs Apple hates A this difference would be captured when you feed them as sequence into RNN but their summation will be same.
I hope you get my point!
Related
For example, I have a paragraph which I want to classify in a binary manner. But because the inputs have to have a fixed length, I need to ensure that every paragraph is represented by a uniform quantity.
One thing I've done is taken every word in the paragraph, vectorized it using GloVe word2vec and then summed up all of the vectors to create a "paragraph" vector, which I've then fed in as an input for my model. In doing so, have I destroyed any meaning the words might have possessed? Considering these two sentences would have the same vector:
"My dog bit Dave" & "Dave bit my dog", how do I get around this? Am I approaching this wrong?
What other way can I train my model? If I take every word and feed that into my model, how do I know how many words I should take? How do I input these words? In the form of a 2D array, where each word vector is a column?
I want to be able to train a model that can classify text accurately.
Surprisingly, I'm getting a high (>90%) for a relatively simple model like RandomForestClassifier just by using this summing up method. Any insights?
Edit: One suggestion I have received is to instead featurize my data as a 2D array where each word is a column, on which a CNN could work. Another suggestion I received was to use transfer learning through the huggingface transformer to get a vector for the whole paragraph. Which one is more feasible?
I want to be able to train a model that can classify text accurately. Surprisingly, I'm getting a high (>90%) for a relatively simple model like RandomForestClassifier just by using this summing up method. Any insights?
If you look up papers on aggregating word embeddings you'll find out that this in fact occurs sometimes, especially if the texts are shorter.
What other way can I train my model? If I take every word and feed that into my model, how do I know how many words I should take? How do I input these words? In the form of a 2D array, where each word vector is a column?
Have you tried keyword extraction? It can alleviate some of the problems with averaging
In doing so, have I destroyed any meaning the words might have
possessed?
As you remarked, you throw out information on word order. But that's not even the worst part: most of the times for longer documents if you embed everything the mean will get dominated by common words ("how", "like", "do" et c). BTW see my answer to this question
Other than that, one trick I've seen is to average word vectors, but subtract first principal component of PCA on word embedding matrix. For details you can see for example this repo which also links to the paper (BTW this paper suggests you can ignore "Smooth Inverse Frequency" stuff since principal component reduction does the useful part).
While I was classifying and clustering the documents written in natural language, I came up with a question ...
As word2vec and glove, and or etc, vectorize the word in distributed spaces, I wonder if there are any method recommended or commonly used for document vectorization USING word vectors.
For example,
Document1: "If you chase two rabbits, you will lose them both."
can be vectorized as,
[0.1425, 0.2718, 0.8187, .... , 0.1011]
I know about the one also known as doc2vec, that this document has n dimensions just like word2vec. But this is 1 x n dimensions and I have been testing around to find out the limits of using doc2vec.
So, I want to know how other people apply the word vectors for applications with steady size.
Just stacking vectors with m words will be formed m x n dimensional vectors. In this case, the vector dimension will not be uniformed since dimension m will depends on the number of words in document.
If: [0.1018, ... , 0.8717]
you: [0.5182, ... , 0.8981]
..: [...]
m th word: [...]
And this form is not favorable form to run some machine learning algorithms such as CNN. What are the suggested methods to produce the document vectors in steady form using word vectors?
It would be great if it is provided with papers as well.
Thanks!
The most simple approach to get a fixed-size vector from a text, when all you have is word-vectors, to average all the word-vectors together. (The vectors could be weighted, but if they haven't been unit-length-normalized, their raw magnitudes from training are somewhat of an indicator of their strength-of-single-meaning – polysemous/ambiguous words tend to have vectors with smaller magnitudes.) It works OK for many purposes.
Word vectors can be specifically trained to be better at composing like this, if the training texts are already associated with known classes. Facebook's FastText in its 'classification' mode does this; the word-vectors are optimized as much or more for predicting output classes of the texts they appear in, as they are for predicting their context-window neighbors (classic word2vec).
The 'Paragraph Vector' technique, often called 'doc2vec', gives every training text a sort-of floating pseudoword, that contributes to every prediction, and thus winds up with a word-vector-like position that may represent that full text, rather than the individual words/contexts.
There are many further variants, including some based on deeper predictive networks (eg 'Skip-thought Vectors'), or slightly different prediction targets (eg neighboring sentences in 'fastSent'), or other genericizations that can even include a mixture of symbolic and numeric inputs/targets during training (an option in Facebook's StarSpace, which explores other entity-vectorization possibilities related to word-vectors and FastText-like classification needs).
If you don't need to collapse a text to fixed-size vectors, but just compare texts, there are also techniques like "Word Mover's Distance" which take the "bag of word-vectors" for one text, and another, and give a similarity score.
I want to find the opinion of a sentence either positive or negative. For example talk about only one sentence.
The play was awesome
If change it to vector form
[0,0,0,0]
After searching through the Bag of words
bad
naughty
awesome
The vector form becomes
[0,0,0,1]
Same for other sentences. Now I want to pass it to the machine learning algorithm for training it. How can I train the network using these multiple vectors? (for finding the opinion of unseen sentences) Obviously not! Because the input is fix in neural network. Is there any way? The above procedure is just my thinking. Kindly correct me if I am wrong. Thanks in advance.
Since your intuitive input format is "Sentence". Which is, indeed, a string of tokens with arbitrary length. Abstracting sentences as token series is not a good choice for many existing algorithms only works on determined format of inputs.
Hence, I suggest try using tokenizer on your entire training set. This will give you vectors of length of the dictionary, which is fixed for given training set.
Because when the length of sentences vary drastically, then size of the dictionary always keeps stable.
Then you can apply Neural Networks(or other algorithms) to the tokenized vectors.
However, vectors generated by tokenizer is extremely sparse because you only work on sentences rather than articles.
You can try LDA (supervised, not PCA), to reduce the dimension as well as amplify the difference.
That will keep the essential information of your training data as well as express your data at fixed size, while this "size" is not too large.
By the way, you may not have to label each word by its attitude since the opinion of a sentence also depends on other kind of words.
Simple arithmetics on number of opinion-expressing words many leave your model highly biased. Better label the sentences and leave the rest job to classifiers.
For the confusions
PCA and LDA are Dimensional Reduction techniques.
difference
Let's assume each tuple of sample is denoted as x (1-by-p vector).
p is too large, we don't like that.
Let's find a matrix A(p-by-k) in which k is pretty small.
So we get reduced_x = x*A, and most importantly, reduced_x must
be able to represent x's characters.
Given labeled data, LDA can provide proper A that can maximize
distance between reduced_x of different classes, and also minimize
the distance within identical classes.
In simple words: compress data, keep information.
When you've got
reduced_x, you can define training data: (reduced_x|y) where y is
0 or 1.
I work on classifying some reviews (paragraphs) consists of multiple sentences. I classified them with bag-of-word features in Weka via libSVM. However, I had another idea which I don't know how to implement :
I thought creating syntactical and shallow-semantics based features per sentence in the reviews is worth to try. However, I couldn't find any way to encode those features sequentially, since a paragraph's sentence size varies. The reason that I wanted to keep those features in an order is that the order of sentence features may give a better clue for classification. For example, if I have two instances P1 (with 3 sentences) and P2 (2 sentences), I would have a space like that (assume each sentence has one binary feature as a or b):
P1 -> a b b /classX
P2 -> b a /classY
So, my question is that whether I can implement that classification of different feature sizes in feature space or not? If yes, is there any kind of classifier that I can use in Weka, scikit-learn or Mallet? I would appreciate any responses.
Thanks
Regardless of the implementation, an SVM with the standard kernels (linear, poly, RBF) requires fixed-length feature vectors. You can encode any information in those feature vectors by encoding as booleans; e.g. collect all syntactical/semantic features that occur in your corpus, then introduce booleans that represent that "feature such and such occurred in this document". If it's important to capture the fact that these features occur in multiple sentences, count them and use put the frequency in the feature vector (but be sure to normalize your frequencies by document length, as SVMs are not scale-invariant).
In case you are classifying textual data, I would suggest looking at "Rational Kernels" which are made on weighted finite transducers for classifying natural language texts. Rational Kernels can be applied on varied length vectors and are already implemented as an open source project (OpenFST).
It is the library's problem, since SVM itself does not require fixed-length feature vectors, it only need a kernel function, if you can provide a kernel function with varied length vector, it should be OK for SVM
Usually one wants to get a feature from a text by using the bag of words approach, counting the words and calculate different measures, for example tf-idf values, like this: How to include words as numerical feature in classification
But my problem is different, I want to extract a feature vector from a single word. I want to know for example that potatoes and french fries are close to each other in the vector space, since they are both made of potatoes. I want to know that milk and cream also are close, hot and warm, stone and hard and so on.
What is this problem called? Can I learn the similarities and features of words by just looking at a large number documents?
I will not make the implementation in English, so I can't use databases.
hmm,feature extraction (e.g. tf-idf) on text data are based on statistics. On the other hand, you are looking for sense (semantics). Therefore no such a method like tf-idef will work for you.
In NLP exists 3 basic levels:
morphological analyses
syntactic analyses
semantic analyses
(higher number represents bigger problems :)). Morphology is known for majority languages. Syntactic analyses is a bigger problem (it deals with things like what is verb, noun in some sentence,...). Semantic analyses has the most challenges, since it deals with meaning which is quite difficult to represent in machines, have many exceptions and are language-specific.
As far as I understand you want to know some relationships between words, this can be done via so-called dependency tree banks, (or just treebank): http://en.wikipedia.org/wiki/Treebank . It is a database/graph of sentences where a word can be considered as a node and relationship as arc. There is good treebank for czech language and for english there will be also some, but for many 'less-covered' languages it can be a problem to find one ...
user1506145,
Here is a simple idea that I have used in the past. Collect a large number of short documents like Wikipedia articles. Do a word count on each document. For the ith document and the jth word let
I = the number of documents,
J = the number of words,
x_ij = the number of times the jth word appears in the ith document, and
y_ij = ln( 1+ x_ij).
Let [U, D, V] = svd(Y) be the singular value decomposition of Y. So Y = U*D*transpose(V)), U is IxI, D is diagonal IxJ, and V is JxJ.
You can use (V_1j, V_2j, V_3j, V_4j) as a feature vector in R^4 for the jth word.
I am surprised the previous answers haven't mentioned word embedding. Word embedding algorithm can produce word vectors for each word a given dataset. These algorithms can nfer word vectors from the context. For instance, by looking at the context of the following sentences we can say that "clever" and "smart" is somehow related. Because the context is almost the same.
He is a clever guy
He is a smart guy
A co-occurrence matrix can be constructed to do this. However, it is too inefficient. A famous technique designed for this purpose is called Word2Vec. It can be studied from the following papers.
https://arxiv.org/pdf/1411.2738.pdf
https://arxiv.org/pdf/1402.3722.pdf
I have been using it for Swedish. It is quite effective in detecting similar words and completely unsupervised.
A package could be find in gensim and tensorflow.