ale3otik/paraphrases-generator

Paraphrases generator based on RAVE.

paraphrases-generator's Issues

Is there a pretrained model ready?

Hi! Thanks for providing this code.

I was planning to just test this on my own sentence pairs and see how well it works. Do you happen to have a pretrained model to share as well? That would be amazing. Thanks!

Eric

Questions on the implementation

Hi Aleksey, had a couple of questions on the implementation, hoping you can get back.

1. How long do you train the model for and did you change any of the hyperparameters mentioned in the paper.
2. In the paper the authors mention that they are learning the embeddings instead of using glove did you see an improvement with glove ?
3. Can you share a pretrained model to bootstrap and reduce training time.

Thanks

About bleu

Hi.I want to know how to use the bleu.py to evaluate the model.Thanks！

any guide to setup the dataset for ready to training?

mldl@ub1604:~/ub16_prj/paraphrases-generator$ python3 train.py
ALL: train: 0, test: 0
Traceback (most recent call last):
File "/usr/local/lib/python3.5/dist-packages/pandas/core/indexes/base.py", line 3078, in get_loc
return self._engine.get_loc(key)
File "pandas/_libs/index.pyx", line 140, in pandas._libs.index.IndexEngine.get_loc
File "pandas/_libs/index.pyx", line 162, in pandas._libs.index.IndexEngine.get_loc
File "pandas/_libs/hashtable_class_helper.pxi", line 1492, in pandas._libs.hashtable.PyObjectHashTable.get_item
File "pandas/_libs/hashtable_class_helper.pxi", line 1500, in pandas._libs.hashtable.PyObjectHashTable.get_item
KeyError: 'question1'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "train.py", line 51, in
batch_loader = BatchLoader(datasets=datasets)
File "/home/mldl/ub16_prj/paraphrases-generator/utils/batch_loader.py", line 61, in init
self.build_vocab(sentences)
File "/home/mldl/ub16_prj/paraphrases-generator/utils/batch_loader.py", line 265, in build_vocab
sentences = self.get_sentences_from_data()
File "/home/mldl/ub16_prj/paraphrases-generator/utils/batch_loader.py", line 250, in get_sentences_from_data
sentences += list(df['question1'].values) + list(df['question2'].values)
File "/usr/local/lib/python3.5/dist-packages/pandas/core/frame.py", line 2688, in getitem
return self._getitem_column(key)
File "/usr/local/lib/python3.5/dist-packages/pandas/core/frame.py", line 2695, in _getitem_column
return self._get_item_cache(key)
File "/usr/local/lib/python3.5/dist-packages/pandas/core/generic.py", line 2489, in _get_item_cache
values = self._data.get(item)
File "/usr/local/lib/python3.5/dist-packages/pandas/core/internals.py", line 4115, in get
loc = self.items.get_loc(item)
File "/usr/local/lib/python3.5/dist-packages/pandas/core/indexes/base.py", line 3080, in get_loc
return self._engine.get_loc(self._maybe_cast_indexer(key))
File "pandas/_libs/index.pyx", line 140, in pandas._libs.index.IndexEngine.get_loc
File "pandas/_libs/index.pyx", line 162, in pandas._libs.index.IndexEngine.get_loc
File "pandas/_libs/hashtable_class_helper.pxi", line 1492, in pandas._libs.hashtable.PyObjectHashTable.get_item
File "pandas/_libs/hashtable_class_helper.pxi", line 1500, in pandas._libs.hashtable.PyObjectHashTable.get_item
KeyError: 'question1'
mldl@ub1604:~/ub16_prj/paraphrases-generator$

How to generate examples of paraphrase sentences?

Looking through the notebooks, I still can't figure out how to generate a paraphrased sentence. Does this package includes function similar to model.predict()? So that it will take a string as input and provide a paraphrased string as output. Thanks in advance.

how to generate sentence by source sentence only?

could you tell me how to generate sentence by source sentence only?