I've been trying to understand self-attention, but everything I found doesn't explain the concept on a high level very well.
Let's say we use self-attention in a NLP task, so our input is a sentence.
Then self-attention can be used to measure how "important" each word in the sentence is for every other word.
The problem is that I do not understand how that "importance" is measured. Important for what?
What exactly is the goal vector the weights in the self-attention algorithm are trained against?
Connecting language with underlying meaning is called grounding. A sentence like “The ball is on the table” results into an image which can be reproduced with multimodal learning. Multimodal means, that different kind of words are available for example events, action words, subjects and so on. A self-attention mechanism works with mapping input vector to output vectors and between them is a neural network. The output vector of the neural network is referencing to the grounded situation.
Let us make a short example. We need a pixel image which is 300x200, we need a sentence in natural language and we need a parser. The parser works in both directions. He can convert text to image, that means the sentence “The ball is on the table” gets converted into the 300x200 image. But it is also possible to parse a given image and extract the natural sentence back. Self-attention learning is a bootstrapping technique to learn and use the grounded relationship. That means to verify existing language models, to learn new one and to predict future system states.
This question is old now but I came across it so I figured I should update others as my own understanding has increased.
Attention simply refers to some operation that takes the output and combines it with some other information. Typically this just happens by taking the dot product of the output with some other vector so it can "attend" to it in some way.
Self-attention combines the output with other parts of the input (hence self part). Again the combination usually occurs via the dot-product between the vectors.
Finally how is attention (or self-attention) trained?
Let's call Z our output, W our weight matrix and X our input (we'll use # as matrix multiplication symbol).
Z = X^T # W^T # X
In NLP we will compare Z to whatever we want the resulting output to be. In machine translation it is the sentence in the other language for example. We can compare the two with average cross entropy loss over each word predicted. Finally we can update W with back propagation.
How do we see what is important? We can look at the magnitudes of Z to see after the attention what words were most "attended" to.
This is a slightly simplified example as it only has one weight matrix and typically the inputs are embedded but I think it still highlights some of the necessary details concerning attention.
Here is a useful resource with visualizations for more information about attention.
Here is another resource with visualizations for more about attention in transformers specifically self-attention.
Related
Take the following sentence:
I'm going to change the light bulb
The meaning of change means replace, as in someone is going to replace the light bulb. This could easily be solved by using a dictionary api or something similar. However, the following sentences
I need to go the bank to change some currency
You need to change your screen brightness
The first sentence does not mean replace anymore, it means Exchangeand the second sentence, change means adjust.
If you were trying to understand the meaning of change in this situation, what techniques would someone use to extract the correct definition based off of the context of the sentence? What is what I'm trying to do called?
Keep in mind, the input would only be one sentence. So something like:
Screen brightness is typically too bright on most peoples computers.
People need to change the brightness to have healthier eyes.
Is not what I'm trying to solve, because you can use the previous sentence to set the context. Also this would be for lots of different words, not just the word change.
Appreciate the suggestions.
Edit: I'm aware that various embedding models can help gain insight on this problem. If this is your answer, how do you interpret the word embedding that is returned? These arrays can be upwards of 500+ in length which isn't practical to interpret.
What you're trying to do is called Word Sense Disambiguation. It's been a subject of research for many years, and while probably not the most popular problem it remains a topic of active research. Even now, just picking the most common sense of a word is a strong baseline.
Word embeddings may be useful but their use is orthogonal to what you're trying to do here.
Here's a bit of example code from pywsd, a Python library with implementations of some classical techniques:
>>> from pywsd.lesk import simple_lesk
>>> sent = 'I went to the bank to deposit my money'
>>> ambiguous = 'bank'
>>> answer = simple_lesk(sent, ambiguous, pos='n')
>>> print answer
Synset('depository_financial_institution.n.01')
>>> print answer.definition()
'a financial institution that accepts deposits and channels the money into lending activities'
The methods are mostly kind of old and I can't speak for their quality but it's a good starting point at least.
Word senses are usually going to come from WordNet.
I don't know how useful this is but from my POV, word vector embeddings are naturally separated and the position in the sample space is closely related to different uses of the word. However like you said often a word may be used in several contexts.
To Solve this purpose, generally encoding techniques that utilise the context like continuous bag of words, or continous skip gram models are used for classification of the usage of word in a particular context like change for either exchange or adjust. This very idea is applied in LSTM based architectures as well or RNNs where the context is preserved over input sequences.
The interpretation of word-vectors isn't practical from a visualisation point of view, but only from 'relative distance' point of view with other words in the sample space. Another way is to maintain a matrix of the corpus with contextual uses being represented for the words in that matrix.
In fact there's a neural network that utilises bidirectional language model to first predict the upcoming word then at the end of the sentence goes back and tries to predict the previous word. It's called ELMo. You should go through the paper.ELMo Paper and this blog
Naturally the model learns from representative examples. So the better training set you give with the diverse uses of the same word, the better model can learn to utilise context to attach meaning to the word. Often this is what people use to solve their specific cases by using domain centric training data.
I think these could be helpful:
Efficient Estimation of Word Representations in
Vector Space
Pretrained language models like BERT could be useful for this as mentioned in another answer. Those models generate a representation based on the context.
The recent pretrained language models use wordpieces but spaCy has an implementation that aligns those to natural language tokens. There is a possibility then for example to check the similarity of different tokens based on the context. An example from https://explosion.ai/blog/spacy-transformers
import spacy
import torch
import numpy
nlp = spacy.load("en_trf_bertbaseuncased_lg")
apple1 = nlp("Apple shares rose on the news.")
apple2 = nlp("Apple sold fewer iPhones this quarter.")
apple3 = nlp("Apple pie is delicious.")
print(apple1[0].similarity(apple2[0])) # 0.73428553
print(apple1[0].similarity(apple3[0])) # 0.43365782
I am coming from Google BERT context (Bidirectional Encoder representations from Transformers). I have gone through architecture and codes. People say this is bidirectional by nature. To make it unidirectional attention some mask is to be applied.
Basically a transformer takes key, values and queries as input; uses encoder decoder architecture; and applies attention to these keys, queries and values. What I understood is we need to pass tokens explicitly rather than transformer understanding this by nature.
Can someone please explain what makes transformer is bidirectional by nature
Bidirectional is actually a carry-over term from RNN/LSTM. Transformer is much more than that.
Transformer and BERT can directly access all positions in the sequence, equivalent to having full random access memory of the sequence during encoding/decoding.
Classic RNN has only access to the hidden state and last token, e.g. encoding of word3 = f(hidden_state, word2), so it has to compress all previous words into a hidden state vector, theoretically possible but a severe limitation in practice. Bidirectional RNN/LSTM is slightly better. Memory networks is another way to work around this. Attention is yet another way to improve LSTM seq2seq models. The insight for Transformer is that you want full memory access and don't need the RNN at all!
Another piece of history: an important ingredient that let us deal with sequence structure without using RNN is positional encoding, which comes from CNN seq2seq model. It would not have been possible without this. Turns out, you don't need the CNN either, as CNN doesn't have full random access, but each convolution filter can only look at a number of neighboring words at a time.
Hence, Transformer is more like FFN, where encoding of word1 = f1(word1, word2, word3), and encoding of word3 = f2(word1, word2, word3). All positions available all the time.
You might also appreciate the beauty which is that the authors made it possible to compute attention for all positions in parallel, through the use of Q, K, V matrices. It's quite magical!
But understand this, you'll also appreciate the limitations of Transformer, that it requires O(N^2 * d) computation where N is the sequence length, precisely because we're doing N*N attention of all words with all other words. RNN, on the other hand, is linear in the sequence length and requires O(N * d^2) computation. d is the dimension of model hidden state.
Transformer just won't write a novel anytime soon!
On the following picture you will see in a really clear way why BERT is Bidirectional.
This is crucial since this forces the model to use information from the entire sentence simultaneously – regardless of the position – to make a good predictions.
BERT has been a clear break through allowed by the use of the notorious "attention is all you need" paper and architecture.
This Bidirectional idea (masked) is different from classic LSTM cells which till now used the forward or the backward method or both but not at the same time.
Edit:
this is done by the transformer. The attention is all you need paper is presenting an encoder-decoder system implementing a sequence to sequence framework. BERT is using this Transformer (sequence to sequence Bidirectional network) to do other NLP task. And this has been done by using a masked approach.
The important thing is: BERT uses Attention but Attention has been done for a translation and as such do not care for Bidirectional. But remove a word and you have Bidirectional.
So why BERT now?
well the Transformer is the first transduction model relying
entirely on self-attention to compute representations of its input and output without using sequencealigned RNNs or convolution. Meaning that this model allows a sentence Embedding far more effective than before. In fact, RNN based architectures are hard to parallelize and can have difficulty learning long-range dependencies within the input and output sequences. SO break through in architecture AND the use of this idea to train a network by masking a word (or more) leads to BERT.
Edit of Edit:
forget about the scale product, it's the inside the Attention which is inside A multi head attention itself inside the Transformer: you are looking to deep. The transformer is using the entire sequence every time to find the other sequence (In case of BERT it's the missing 0.15 percentage of the sentence) and that's it. The use of BERT as a language model is realy a transfer learning (see this)
As stated in your post, unidirectional can be done with a certain type of mask, bidirec is better. And it is used because the go from a full sentence to a full sentence but not the way classic Seq2seq is made (with LSTM and RNN) and as such can be used for LM.
BERT is a bidirectional transformer whereas the original transformer (Vaswani et al., 2017) is unidirectional. This can be shown by comparing the masks in the code.
Original Transformer
Tensorflow's tutorial is a good reference. The look_ahead_mask is what makes the Transformer unidirectional.
def create_look_ahead_mask(size):
mask = 1 - tf.linalg.band_part(tf.ones((size, size)), -1, 0)
return mask # (seq_len, seq_len)
If you trace the code, you can find the look_ahead_mask is applied to the attention_weights in the decoder. Basically each row in the attention_weights represents a attention query for token at certain position (the first row -> first token position; the second row -> second token position etc.). And the look_ahead_mask blacks out the tokens appear after this position in the decoder so it does not see the "future". In that sense, the decoder is unidirectional analogous to unidirectional in an RNN.
BERT
On the other hand, if you check the original BERT implementation (also in Tensorflow). There's only an optional input_mask applied to the entire BertModel. And if you follow the README on pre-training the model and run create_pretraining_data.py, you will observe that the input_mask is only used for padding the input sequence so for short sentences the unused tokens are ignored. Thus, attention in BERT can be applied to both the "past" and the "future" of a given token position. In that sense, the encoder in BERT is bidirectional analogous to bidirectional in an RNN.
I know this is an old post but for anyone coming back to this:
Adding to what Hai-Anh Trinh said, Transformers aren't 'bi-directional', it would be better to call them "omni-directional". Because of their self-attention method, they are able to consider every single word at the same time, simultaneously.
BERT on the other hand is "deeply bidirectional". This is because of the masked language model(MLM) pre-training objective that is used in BERT. (there are a lot of resources online, I can link some if need be)
It's easy to get confused so don't worry about it.
(https://arxiv.org/pdf/1810.04805.pdf; link to the original BERT paper)
(https://arxiv.org/pdf/1706.03762.pdf; link to the original Transformer paper)
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.
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!
Binarization is the act of transforming colorful features of of an entity into vectors of numbers, most often binary vectors, to make good examples for classifier algorithms.
If we where to binarize the sentence "The cat ate the dog", we could start by assigning every word an ID (for example cat-1, ate-2, the-3, dog-4) and then simply replace the word by it's ID giving the vector <3,1,2,3,4>.
Given these IDs we could also create a binary vector by giving each word four possible slots, and setting the slot corresponding to a specific word with to one, giving the vector <0,0,1,0,1,0,0,0,0,1,0,0,0,0,0,1>. The latter method is, as far as I know, is commonly referred to as the bag-of-words-method.
Now for my question, what is the best binarization method when it comes to describe features for natural language processing in general, and transition-based dependency parsing (with Nivres algorithm) in particular?
In this context, we do not want to encode the whole sentence, but rather the current state of the parse, for example the top word on the stack en the first word in the input queue. Since order is highly relevant, this rules out the bag-of-words-method.
With best, I am referring to the method that makes the data the most intelligible for the classifier, without using up unnecessary memory. For example I don't want a word bigram to use 400 million features for 20000 unique words, if only 2% the bigrams actually exist.
Since the answer is also depending on the particular classifier, I am mostly interested in maximum entropy models (liblinear), support vector machines (libsvm) and perceptrons, but answers that apply to other models are also welcome.
This is actually a really complex question. The first decision you have to make is whether to lemmatize your input tokens (your words). If you do this, you dramatically decrease your type count, and your syntax parsing gets a lot less complicated. However, it takes a lot of work to lemmatize a token. Now, in a computer language, this task gets greatly reduced, as most languages separate keywords or variable names with a well defined set of symbols, like whitespace or a period or whatnot.
The second crucial decision is what you're going to do with the data post-facto. The "bag-of-words" method, in the binary form you've presented, ignores word order, which is completely fine if you're doing summarization of a text or maybe a Google-style search where you don't care where the words appear, as long as they appear. If, on the other hand, you're building something like a compiler or parser, order is very much important. You can use the token-vector approach (as in your second paragraph), or you can extend the bag-of-words approach such that each non-zero entry in the bag-of-words vector contains the linear index position of the token in the phrase.
Finally, if you're going to be building parse trees, there are obvious reasons why you'd want to go with the token-vector approach, as it's a big hassle to maintain sub-phrase ids for every word in the bag-of-words vector, but very easy to make "sub-vectors" in a token-vector. In fact, Eric Brill used a token-id sequence for his part-of-speech tagger, which is really neat.
Do you mind if I ask what specific task you're working on?
Binarization is the act of
transforming colorful features of
an entity into vectors of numbers,
most often binary vectors, to make
good examples for classifier
algorithms.
I have mostly come across numeric features that take values between 0 and 1 (not binary as you describe), representing the relevance of the particular feature in the vector (between 0% and 100%, where 1 represents 100%). A common example for this are tf-idf vectors: in the vector representing a document (or sentence), you have a value for each term in the entire vocabulary that indicates the relevance of that term for the represented document.
As Mike already said in his reply, this is a complex problem in a wide field. In addition to his pointers, you might find it useful to look into some information retrieval techniques like the vector space model, vector space classification and latent semantic indexing as starting points. Also, the field of word sense disambiguation deals a lot with feature representation issues in NLP.
[Not a direct answer] It all depends on what you are try to parse and then process, but for general short human phrase processing (e.g. IVT) another method is to use neural networks to learn the patterns. This can be very acurate for smallish vocubularies