I am new to stackoverflow. Please forgive my bad English.
I am using word2vec for a school project. I want to work with a domain specific corpus (like Physics Textbook) for creating the word vectors using Word2Vec. This standalone does not provide good results due to lesser size of the corpus. This especially hurts as we want to evaluate on words that may very well be outside the vocabulary of the text book.
We want the textbook to encode the domain specific relationships and semantic "nearness". "Quantum" and "Heisenberg" are especially close in this textbook for eg. which may not hold true for background corpus. To handle the generic words (like "any") we need the basic background model(like the one provided by Google on word2vec site).
Is there any way that we can supplant to the background model using our newer corpus. Just training on the corpus etc. doesnot work well.
Are there any attempts to combine vector representations from two corpus- general and specific. I could not find any in my searches.
Let's talk about gensim since you tagged you question with it. You can load a previously trained model in python using gensim. Then you continue training it. Would it be useful?
# load from previous gensim file:
model = gensim.models.Word2Vec.load(fname)
# or from word2vec c format:
# model = gensim.models.Word2Vec.load_word2vec_format('/path/vectors.bin', binary=True)
# continue training:
model.train(other_sentences)
model.save(fname)
Related
How to find list of Out Of Vocabulary (OOV) words from my domain spectific pdf while using FastText model? I need to fine tune FastText with my domain specific words.
A FastText model will already be able to generate vectors for OOV words.
So there's not necessarily any need to either list the specifically OOV words in your PDF, nor 'fine tune' as FastText model.
You just ask it for vectors, it gives them back. The vectors for full in-vocabulary words, that were trained from relevant training material, will likely be best, while vectors synthesized for OOV words from word-fragments (character n-grams) shared with training material will just be rough guesses - better than nothing, but not great.
(To train a good word-vector requires many varied examples of a word's use, interleaved with similarly good examples of its many 'peer' words – and traditionally, in one unified, balanced training session.)
If you think you need to do more, you should expand your questin with more details about why you think that's necessary, and what existing precedents (in docs/tutorials/papers) you're trying to match.
I've not seen a well-documented way to casually fine-tune, or incrementally expand the known-vocabulary of, an existing FastText model. There would be a lot of expert tradeoffs required, and in many cases simply training a new model with sufficient data is likely to be a safer approach.
Anyone seeking such fine-tuning should have a clear idea of:
what their incremental data might be able to add to an existing model
what process/code will they be using, and why that process/code might be expected to give meaningful results with their specific starting model & new data
how the results of any such process can be evaluated to ensure the extra fine-tuning steps are beneficial compared to alternatives
I want to fine tune BERT on a specific domain. I have texts of that domain in text files. How can I use these to fine tune BERT?
I am looking here currently.
My main objective is to get sentence embeddings using BERT.
The important distinction to make here is whether you want to fine-tune your model, or whether you want to expose it to additional pretraining.
The former is simply a way to train BERT to adapt to a specific supervised task, for which you generally need in the order of 1000 or more samples including labels.
Pretraining, on the other hand, is basically trying to help BERT better "understand" data from a certain domain, by basically continuing its unsupervised training objective ([MASK]ing specific words and trying to predict what word should be there), for which you do not need labeled data.
If your ultimate objective is sentence embeddings, however, I would strongly suggest you to have a look at Sentence Transformers, which is based on a slightly outdated version of Huggingface's transformers library, but primarily tries to generate high-quality embeddings. Note that there are ways to train with surrogate losses, where you try to emulate some form ofloss that is relevant for embeddings.
Edit: The author of Sentence-Transformers recently joined Huggingface, so I expect support to greatly improve over the upcoming months!
#dennlinger gave an exhaustive answer. Additional pretraining is also referred as "post-training", "domain adaptation" and "language modeling fine-tuning". here you will find an example how to do it.
But, since you want to have good sentence embeddings, you better use Sentence Transformers. Moreover, they provide fine-tuned models, which already capable of understanding semantic similarity between sentences. "Continue Training on Other Data" section is what you want to further fine-tune the model on your domain. You do have to prepare training dataset, according to one of available loss functions. E.g. ContrastLoss requires a pair of texts and a label, whether this pair is similar.
I believe transfer learning is useful to train the model on a specific domain. First you load the pretrained base model and freeze its weights, then you add another layer on top of the base model and train that layer based on your own training data. However, the data would need to be labelled.
Tensorflow has some useful guide on transfer learning.
You are talking about pre-training. Fine-tuning on unlabeled data is called pre-training and for getting started, you can take a look over here.
I am trying to train a model to classify tweets using opennlp. My question is should I perform tokenization, stop word removal etc on the tweets which I am using for training the model or should I use the tweet directly without performing the sanitization?
It really depends on what you are training:
If your algorithm is designed to recieve simple text and it performs all the simplification by itself before using the machine learning techniques on it you should provide pairs of the type
Otherwise if you are just trianing a black box I would say that if your model is going to work on a certain type of features, in your case tokenized and stemmed word it should be trained on this type of data so provide
I have been trying to use NER feature of NLTK. I want to extract such entities from the articles. I know that it can not be perfect in doing so but I wonder if there is human intervention in between to manually tag NEs, will it improve?
If yes, is it possible with present model in NLTK to continually train the model. (Semi-Supervised Training)
The plain vanilla NER chunker provided in nltk internally uses maximum entropy chunker trained on the ACE corpus. Hence it is not possible to identify dates or time, unless you train it with your own classifier and data(which is quite a meticulous job).
You could refer this link for performing he same.
Also, there is a module called timex in nltk_contrib which might help you with your needs.
If you are interested to perform the same in Java better look into Stanford SUTime, it is a part of Stanford CoreNLP.
How to get word vector representation when using Deep Learning in NLP ? The words are represented by a fixed length vector, see http://machinelearning.wustl.edu/mlpapers/paper_files/BengioDVJ03.pdf for more details.
Deep Learning and NLP are quite complex subjects, so if you really want to understand them you'll need to follow a couple of courses in the field and read many papers. There are lots of different techniques for converting words into vector representations and it's a very active area of research. Socher's DL for NLP tutorial is a good next step if you are already well acquainted with NLP and Machine Learning (including deep learning).
With that said (and considering it's a programming forum), if you are just interested for now in using someone's else tools to quickly obtain vector representations which can be useful in some tasks, one library which you must look at is word2vec. Take a look in its website: https://code.google.com/p/word2vec/. It's a very powerful tool and for some basic stuff it could be used without much knowledge.
For getting word vector for a word you can use Google News 300 dimensional word vector model.
Download the model from here - https://drive.google.com/file/d/0B7XkCwpI5KDYNlNUTTlSS21pQmM/edit?usp=sharing OR from here
https://s3.amazonaws.com/mordecai-geo/GoogleNews-vectors-negative300.bin.gz .
After downloading load the model using gensim python library as below -
import gensim
# Load Google's pre-trained Word2Vec model.
model = gensim.models.Word2Vec.load_word2vec_format('./model/GoogleNews-vectors-negative300.bin', binary=True)
Then just query the model for word vector corresponding to a word like
model['usa']
And it returns you a 300 dimensional word vector for usa.
Note that you may not found word vectors for all the words in this model.
Also instead of this Google News model, other models can also be used.