Well, I think concatenating all documents is not really necessary, just easier (and more efficient computationally).
I would imagine taking a bucket of similar-length sequences, bptt-ing through them from their beginning to end (using PackedSequences to avoid padding), and then taking a next bucket of sequences.
Well, what I meant was:
take the general LM (trained on wikitext)
fine-tune the LM on the downstream task’s dataset
add the classifier head to the LM, without removing the old one, train both further.
The hypothesis: on a small dataset of short text, fine-tuning the classifier might make the encoder “forget” the language. It also might not, and I guess it is not that easy to test.
Hello guys) First of all, I woud like to thank you for all the hard work you are doing to make it easier for us following behind.
To @piotr.czapla
I’m working on training russian language model and I have a couple of questions.
My lm training steps are: exp = LMHyperParams(dataset_path='data/wiki/ru-100/', qrnn=False, tokenizer='v', lang='ru', name='russian') learn = exp.create_lm_learner(data_lm=data_lm) learn.unfreeze() learn.fit_one_cycle(20, 1e-3, moms=(0.8,0.7))
I would like to test a model on the upstream task (text classification) and use functionality of ulmfit.train_clas. Speaking of questions:
How could I use trained lm in classification task? My suggestion is something like this: exp = CLSHyperParams('data/my_class_task_data') exp.pretrained_fnames = path.to_my_best_model
Is my suggestion right or do i miss something?
If I use other than imdb task for classification and wish to apply CLSHyperParams, do I need to recreate my_task data directory structure the same way as imdb data structure?
What is a good choice of vocabulary size to train LM from wiki from scratch?
Hey. My dataset is a mixture of French and English and I have a classification problem. Can you give me some advice on using Ulmfit? Should I train a new LM on mixed French and English wiki? Thanks
Is the text within a document in your dataset multi-language or is each document in only one of multiple languages? If the latter is the case, you can use something like the langdetect Python library. Run detect_language() to find the probabilities for each language and remove the document if the probability for your language is below a given threshold.
In my case I have a dataset of book reviews that are mostly in Dutch. Some reviewers have translated the Dutch review into other languages, so I use langdetect to remove these multi-language documents from the dataset.
Hi, thanks for the response.
I tried langdetect but as my dataset consists from descriptions which are not very long, it found ‘wrong’ languages with very high probability.
So having the fact that I cant detect language, I am thinking of training a new model from scratch based on French and English wiki and would like to get an advise.
Thanks
you would have to fill all the hyper params then. It is easier to train the LM with LMHyperParams then load it using CLSHyperParams.from_lm(dataset_path, base_lm_path). So in your case:
exp = CLSHyperParams.from_lm('data/my_class_task_data', 'data/wiki/ru-100/models/v70k/lstm_russian.m', name='russian') # get the exact name of your model from execution of LMHyperParams
Thank you @piotr.czapla. As for now i’m working on the level of fastai abstraction to make it more simple (for me) to understand all the logic. I’m trying to work on upstream classification tasks and get near the best results (in comparison with current benchmark - http://text-machine.cs.uml.edu/projects/rusentiment/).
Next I’ll try to increase the amount of domainspecific (twiter) data for LM finetuning to see if it helps on upstream classification task.
Later I’ll experiment with different tokenizers and try to addapt train_clas.py to my data.
@ademyanchuk Perfect ! Can you create a “ULMFiT - Russian” page and put it on the top page of Language Model Zoo? @ppleskov was working on the Russian model in the past but I don’t think he managed to beat the SOTA Russian Sentiment Analysies, He was using the following benchmark: http://www.dialog-21.ru/evaluation/2016/sentiment/
and it turned out to be easy task to classify, i get near .98 f1. Check my solution twice on any bugs, but cant find something. So I believe ruSentEval is beaten.
I’m very happy to share the Dutch dataset and the weights of the trained language model!
However, for the former, I’m not sure whether I can publish it, since the contents are scraped. I’ve read the website’s disclaimer and there’s nothing in it that forbids it, but I’m still not quite sure about legal issues
For language model weights, do you have pointers how I can best package and describe it? I’ve never shared network weights before.
I still wanted to give credits to the owners of the website and its reviewers, so I’ve sent them an email to see if they’re open for this kind of publication. I’ve already tidied up my code and the dataset itself, so it’s ready for publication. I’m just waiting for a response from them now… Fingers crossed!
@piotr.czapla: considering recent developments in the FastAI library, what’s the status of ulmfit-multilingual? I’ve used slightly edited versions of those scripts to generate a language model for Dutch. Is this still the way to go?
@benjaminvdb, Good work, and on time so we can add it to the paper that summarise multilingual ULMFiT.
Recently @mkardas made ulmfit-multlingual compatible with the fastai, we have it in a separate branch that I’m looking in to merging to master tomorrow.
Gals & Guys we are summarising the work on ulmfit-multilingual, and @sebastianruder is writing a short paper.
I’m going through the forum threads and I’m adding ppl that contributed some interesting tests to a private thread, but there is a chance I’ve missed something. If you feel you should be added please let me know.
You can check if you are in the thread by following this link. If I missed you please let me know on private message or thread @ mention me in your language that shows the results.
The paper has a deadline soon (end of Feb). If you would like your results to be added we need to have a pull request by next week that includes:
the code to download your dataset
the “.md” with the results
and links to pretrained LM weights.
So we can run the classification task to double check the results are reproducible without need to train the full LM. If you happen to contribute to the language covered by MLDoc the LM’s won’t be necessery as we will have both lstm and qrnn based one.
Just to chip in, everyone who contributed a dataset and achieved good results that we can reproduce on the data will be included on the paper. Please provide additionally the following information in the PR so that it will be easier to attribute the work:
Finalizing results for Thai to use fastai 1.0.38 and above (previous results and datasets are based on 1.0.22). Do you have a hard deadline for the pull request? @sebastianruder
