I am using gensim Word2Vec model to train word embeddings. My code is:
w2v_model = Word2Vec(min_count=20,
window=2,
vector_size=50,
sample=6e-5,
alpha=0.03,
min_alpha=0.0007,
negative=20,
workers=cores-1)
w2v_model.build_vocab(sentences, progress_per=10000)
w2v_model.train(sentences, total_examples=w2v_model.corpus_count, epochs=50, report_delay=1)
I wonder whether I can access the negative and positive word samples during the process?
Thanks in advance.
Deep inside the training loops, for each individual 'center' word in the training texts that is to be predicted – a micro-training-example for the shallow neural-net – a different set of negative words will be chosen.
Those negative-words will be used for just that one set of forward/backward neural-net nudges, then discarded when training moves to the next word.
There's no way to access them other than changing that core code – which is actually written in Cython, & re-compiled into a native library after any changes. (It's a bit harder to tinker with than pure Python code.)
You can see where the exact choice-of-negative samples happens in the source code for one of the modes (CBOW w/ negative-sampling) here:
https://github.com/RaRe-Technologies/gensim/blob/91175ddc7e3d6f3a2af245c20af21ec3bf5e360f/gensim/models/word2vec_inner.pyx#L427
If you just need a representative set of negative-words, you could copy these steps in your own code.
If you want to know (& potentially log?) the negative words chosen for every positive prediction, I suspect that's a misguided idea:
Meaningful analysis of this algorithm's behavior won't depend on either individual micro-examples, nor the arbitrarily-random negative words chosen over all training. The interesting properties only arise from the tug-of-war happening across the interplay of all training.
As this is very deep in the training loops, even the most-efficient extra-steps, as a function of the negative-words, would slow things down a lot. Or, in the case of logging, result in 20x (for window=20) more logged-negative-words than your original training corpus. For the kinds of large corpora where this algorithm works well, such a slowdown/log could be onerous; for tiny toy-sized examples, this algorithm won't be working interestingly at all.
So the mere question, if you truly want a peek at all the (random, arbitrary) negative words during the process, suggests you may be going down a questionable path.
It'd be easier for me to imagine just wanting to see a representative set of the negatively-sampled words - because any 10, or 10,000, or 1,000,000 such randomly-chosen words are as good as any other, and the algorithm (on adequately-sized data) is robust against usual variance in which negative-words are actually chosen. And for that, you could just run the same sampling-process outside the training.
Separately: those are odd non-default choices for alpha & min_alpha - values that usually don't need any tweaking, and if tweaked should really only be done so with a conscious plan, driven by quantitaive evaluations comparing the results of alternate values. But, those specific odd unmotivated values are pretty common in some of the worst online tutorials. So beware where you're learning about word2vec!
Related
I am using K-means for topic modelling using Word2Vec and would like to understand the implications of vectorizing up to, let's say, 10 dimensions, against embedding it with 200 dimensions and then using PCA to get down to 10. Does the second approach make sense at all?
Which one worked better for your specific purposes, & your specific data, after trying both & comparing the end-results against each other, either in some ad-hoc ("eyeballing") or rigorous way?
There's no reason to prematurely reject any approach, given how many details about your data & ultimate end-goals are unstated.
It would be atypical to train a word2vec model to have only 10 dimensions. Published work most often shows the use of 100 to 1000 dimensions, often 300 or 400, assuming you've got enough bulk training data to make the algorithm worthwhile.
(Word2vec needs a lot of varied training text, with many contrasting usage examples for every word of interest, to generate good results. You may occasionally see toy-sized demos, on smaller amounts of data, just to quickly show steps, or some major qualities of the results. But good results, in the aspects for which word2vec is most appreciated, depend on plentiful training data.)
Also, whether or not your aims would be helped by the extra step of PCA to reduce the dimensionality of a larger word2vec model seems another separable question, to be determined experimentally by comparing results with and without that step, on your actual data/problem, rather than guessed at from intuitions from other projects that might not be comparable.
I want to train a Doc2Vec model with a generic corpus and, then, continue training with a domain-specific corpus (I have read that is a common strategy and I want to test results).
I have all the documents, so I can build and tag the vocab at the beginning.
As I understand, I should train initially all the epochs with the generic docs, and then repeat the epochs with the ad hoc docs. But, this way, I cannot place all the docs in a corpus iterator and call train() once (as it is recommended everywhere).
So, after building the global vocab, I have created two iterators, the first one for the generic docs and the second one for the ad hoc docs, and called train() twice.
Is it the best way or it is a more appropriate way?
If the best, how I should manage alpha and min_alpha? Is it a good decision not to mention them in the train() calls and let the train() manage them?
Best
Alberto
This is probably not a wise strategy, because:
the Python Gensim Doc2Vec class hasn't ever properly supported expanding its known vocabulary after a 1st single build_vocab() call. (Up through at least 3.8.3, such attempts typically cause a Segmentation Fault process crash.) Thus if there are words that are only in your domain-corpus, an initial typical initialization/training on the generic-corpus would leave them out of the model entirely. (You could work around this, with some atypical extra steps, but the other concerns below would remain.)
if there is truly an important contrast between the words/word-senses used in your generic and the different words/word-senses used in your domain corpus, influence of the words from the generic corpus may not be beneficial, diluting domain-relevant meanings
further, any followup training that just uses a subset of all documents (the domain corpus) will only be updating the vectors for that subset of words/word-senses, and the model's internal weights used for further unseen-document inference, in directions that make sense for the domain-corpus alone. Such later-trained vectors may be nudged arbitrarily far out of comparable alignment with other words not appearing in the domain-corpus, and earlier-trained vectors will find themselves no longer tuned in relation to the model's later-updated internal-weights. (Exactly how far will depend on the learning-rate alpha & epochs choices in the followup training, and how well that followup training optimizes model loss.)
If your domain dataset is sufficient, or can be grown with more domain data, it may not be necessary to mix in other training steps/data. But if you think you must try that, the best-grounded approach would be to shuffle all training data together, and train in one session where all words are known from the beginning, and all training examples are presented in balanced, interleaved fashion. (Or possibly, where some training texts considered extra-important are oversampled, but still mixed in with the variety of all available documents, in all epochs.)
If you see an authoritative source suggesting such a "train with one dataset, then another disjoint dataset" approach with the Doc2Vec algorithms, you should press them for more details on what they did to make that work: exact code steps, and the evaluations which showed an improvement. (It's not impossible that there's some way to manage all the issues! But I've seen many vague impressions that this separate-pretraining is straightforward or beneficial, and zero actual working writeups with code and evaluation metrics showing that it's working.)
Update with respect to the additional clarifications you provided at https://stackoverflow.com/a/64865886/130288:
Even with that context, my recommendation remains: don't do this segmenting of training into two batches. It's almost certain to degrade the model compared to a combined training.
I would be interested to see links to the "references in the literature" you allude to. They may be confused or talking about algorithms other than the Doc2Vec ("Paragraph Vectors") algorithm.
If there is any reason to give your domain docs more weight, a better-grounded way would be to oversample them in the combined corpus.
Bu by all means, test all these variants & publish the relative results. If you're exploring shaky hypotheses, I would ignore any advice from StackOverflow-like sources & just run all the variants that your reading of the literature suggest, to see which, if any actually help.
You're right to recognized that the choice of alpha parameters is a murky area that could majorly influence what impact such add-on training has. There's no right answer, so you'll have to search-for and reason-out what might make sense. The inherent issues I've mentioned with such subset-followup-training could make it so that even if you find benefits in some combos, they may be more a product of a lucky combination of data & arbitrary parameters than a generalizable practice.
And: your specific question "if it is better to set such values or not provide them at all" reduces to: "do you want to use the default values, or values set when the model was created, or not?"
Which values might be workable, if at all, for this unproven technique is something that'd need to be experimentally discovered. That is, if you wanted to have comparable (or publishable) results here, I think you'd have to justify from your own novel work some specific strategy for choosing good alpha/epochs and other parameters, rather than adopt any practice merely recommended in a StackOverflow answer.
I want to train two word2vec/GLoVe models on different corpora and then compare the vectors of a single word. I know that it makes no sense to do so as different models start at different random states, but what if we use pre-trained word vectors as the starting point. Can we assume that the two models will continue to build upon the pre-trained vectors by incorporating the respective domain-specific knowledge, and not go into completely different states?
Tried to find some research papers which discuss this problem, but couldn't find any.
Simply starting your models with pre-trained bectors would eliminate some of the randomness, but with each training epoch on your new corpora:
there's still randomness introduced by negative-sampling (if using that default mode), by frequent-word downsampling (if using default values of the sample parameter in word2vec), and by the interplay of different threads
each epoch with your new corpora will be pulling the word-vectors for present words to new, better positions for that corpora, but leaving original words unmoved. The net movements over many epochs could move words arbitrarily far from where they started, in response to the whole-corpus-effects on all words.
So, doing so wouldn't necessarily achieve your goal in a reliable (or theoretically-defensible) way, though it might kinda-work – at least better than starting from purely random initialization – especially if your corpora are small and you do few training epochs. (That's usually a bad idea – you want big varied training data and enough passes for extra passes to make little incremental difference. But doing those things "wrong" could make your results look "better" in this scenario, where you don't want your training to change the original coordinate-space "too much". I wouldn't rely on such an approach.)
Especially if the words you need to compare are a small subset of the total vocabulary, a couple things you could consider:
combine the corpora into one training corpus, shuffled together, but for those words you need to compare, replace them with corpora-specific tokens. For example, replace 'sugar' with 'sugar_c1' and 'sugar_c2' – leaving the vast majority of surrounding words to be the same tokens (and thus learn a single vector across the whole corpus). Then, the two variant tokens for the "same word" will learn different vectors, based on their differing contexts that still share many of the same tokens.
using some "anchor set" of words that you know (or confidently conjecture) either do mean the same across both contexts, or should mean the same, train two models but learn a transformation between the two space based on those guide words. Then, when you apply that transformation to other words, that weren't used to learn the transformation, they'll land in contrasting positions in each others' spaces, maybe achieving the comparison you need. This is a technique that's been used for language-to-language translation, and there's a helper class and example notebook included with the Python gensim library.
There may be other better approaches, these are just two quick ideas that might work without much change to existing libraries. A project like 'HistWords', which used word-vector training to try to track evolving changes in word-meaning over time, might also have ideas for usable techniques.
I'm vectorizing words on a few different corpora with Gensim and am getting results that are making me rethink how Word2Vec functions. My understanding was that Word2Vec was deterministic, and that the position of a word in a vector space would not change from training to training. If "My cat is running" and "your dog can't be running" are the two sentences in the corpus, then the value of "running" (or its stem) seems necessarily fixed.
However, I've found that that value indeed does vary across models, and words keep changing where they are on a vector space when I train the model. The differences are not always hugely meaningful, but they do indicate the existence of some random process. What am I missing here?
This is well-covered in the Gensim FAQ, which I quote here:
Q11: I've trained my Word2Vec/Doc2Vec/etc model repeatedly using the exact same text corpus, but the vectors are different each time. Is there a bug or have I made a mistake? (*2vec training non-determinism)
Answer: The *2vec models (word2vec, fasttext, doc2vec…) begin with random initialization, then most modes use additional randomization
during training. (For example, the training windows are randomly
truncated as an efficient way of weighting nearer words higher. The
negative examples in the default negative-sampling mode are chosen
randomly. And the downsampling of highly-frequent words, as controlled
by the sample parameter, is driven by random choices. These
behaviors were all defined in the original Word2Vec paper's algorithm
description.)
Even when all this randomness comes from a
pseudorandom-number-generator that's been seeded to give a
reproducible stream of random numbers (which gensim does by default),
the usual case of multi-threaded training can further change the exact
training-order of text examples, and thus the final model state.
(Further, in Python 3.x, the hashing of strings is randomized each
re-launch of the Python interpreter - changing the iteration ordering
of vocabulary dicts from run to run, and thus making even the same
string-of-random-number-draws pick different words in different
launches.)
So, it is to be expected that models vary from run to run, even
trained on the same data. There's no single "right place" for any
word-vector or doc-vector to wind up: just positions that are at
progressively more-useful distances & directions from other vectors
co-trained inside the same model. (In general, only vectors that were
trained together in an interleaved session of contrasting uses become
comparable in their coordinates.)
Suitable training parameters should yield models that are roughly as
useful, from run-to-run, as each other. Testing and evaluation
processes should be tolerant of any shifts in vector positions, and of
small "jitter" in the overall utility of models, that arises from the
inherent algorithm randomness. (If the observed quality from
run-to-run varies a lot, there may be other problems: too little data,
poorly-tuned parameters, or errors/weaknesses in the evaluation
method.)
You can try to force determinism, by using workers=1 to limit
training to a single thread – and, if in Python 3.x, using the
PYTHONHASHSEED environment variable to disable its usual string hash
randomization. But training will be much slower than with more
threads. And, you'd be obscuring the inherent
randomness/approximateness of the underlying algorithms, in a way that
might make results more fragile and dependent on the luck of a
particular setup. It's better to tolerate a little jitter, and use
excessive jitter as an indicator of problems elsewhere in the data or
model setup – rather than impose a superficial determinism.
While I don't know any implementation details of Word2Vec in gensim, I do know that, in general, Word2Vec is trained by a simple neural network with an embedding layer as the first layer. The weight matrix of this embedding layer contains the word vectors that we are interested in.
This being said, it is in general also quite common to initialize the weights of a neural network randomly. So there you have the origin of your randomness.
But how can the results be different, regardless of different (random) starting conditions?
A well trained model will assign similar vectors to words that have similar meaning. This similarity is measured by the cosine of the angle between the two vectors. Mathematically speaking, if v and w are the vectors of two very similar words then
dot(v, w) / (len(v) * len(w)) # this formula gives you the cosine of the angle between v and w
will be close to 1.
Also, it will allow you to do arithmetics like the famous
king - man + woman = queen
For illustration purposes imagine 2D-vectors. Would these arithmetical properties get lost if you e.g. rotate everything by some angle around the origin? With a little mathematical background I can assure you: No, they won't!
So, your assumption
If "My cat is running" and "your dog can't be running" are the two
sentences in the corpus, then the value of "running" (or its stem)
seems necessarily fixed.
is wrong. The value of "running" is not fixed at all. What is (somehow) fixed, however, is the similarity (cosine) and arithmetical relationship to other words.
I am trying to do document classification using Support Vector Machines (SVM). The documents I have are collection of emails. I have around 3000 documents to train the SVM classifier and have a test document set of around 700 for which I need classification.
I initially used binary DocumentTermMatrix as the input for SVM training. I got around 81% accuracy for the classification with the test data. DocumentTermMatrix was used after removing several stopwords.
Since I wanted to improve the accuracy of this model, I tried using LSA/SVD based dimensional reduction and use the resulting reduced factors as input to the classification model (I tried with 20, 50, 100 and 200 singular values from the original bag of ~ 3000 words). The performance of the classification worsened in each case. (Another reason for using LSA/SVD was to overcome memory issues with one of the response variable that had 65 levels).
Can someone provide some pointers on how to improve the performance of LSA/SVD classification? I realize this is general question without any specific data or code but would appreciate some inputs from the experts on where to start the debugging.
FYI, I am using R for doing the text preprocessing (packages: tm, snowball,lsa) and building classification models (package: kernelsvm)
Thank you.
Here's some general advice - nothing specific to LSA, but it might help improving the results nonetheless.
'binary documentMatrix' seems to imply your data is represented by binary values, i.e. 1 for a term existing in a document, and 0 for non-existing term; moving to other scoring scheme
(e.g. tf/idf) might lead to better results.
LSA is a good metric for dimensional reduction in some cases, but less so in others. So depending in the exact nature of your data, it might be a good idea to consider additional methods, e.g. Infogain.
If the main incentive for reducing the dimensionality is the one parameter with 65 levels, maybe treating this parameter specifically, e.g. by some form of quantization, would lead to a better tradeoff?
This might not be the best tailored answer. Hope these suggestions may help.
Maybe you could use lemmatization over stemming to reduce unacceptable outcomes.
Short and dense: http://nlp.stanford.edu/IR-book/html/htmledition/stemming-and-lemmatization-1.html
The goal of both stemming and lemmatization is to reduce inflectional forms and
sometimes derivationally related forms of a word to a common base form.
However, the two words differ in their flavor. Stemming usually refers to a crude
heuristic process that chops off the ends of words in the hope of achieving this
goal correctly most of the time, and often includes the removal of derivational
affixes. Lemmatization usually refers to doing things properly with the use of a
vocabulary and morphological analysis of words, normally aiming to remove
inflectional endings only and to return the base or dictionary form of a word,
which is known as the lemma.
One instance:
go,goes,going ->Lemma: go,go,go ||Stemming: go, goe, go
And use some predefined set of rules; such that short term words are generalized. For instance:
I'am -> I am
should't -> should not
can't -> can not
How to deal with parentheses inside a sentence.
This is a dog(Its name is doggy)
Text inside parentheses often referred to alias names of the entities mentioned. You can either removed them or do correference analysis and treat it as a new sentence.
Try to use Local LSA, which can improve the classification process compared to Global LSA. In addition, LSA's power depends entirely on its parameters, so try to tweak parameters (start with 1, then 2 or more) and compare results to enhance the performance.