OpenNMT/openmt

Discussion about OpenNMT (deprecated, use OpenNMT-py instead)

SantoshSanas

@SantoshSanas

Thanks Jean!!!

Shivani Poddar

@shivanipoddariiith

Hi, I was hoping to add context vectors for each source sentence to condition the decoder output in the baseline Encoder-Decoder Architecture for ONMT. The task to integrate these in the TextDataset is seemingly non-trivial. Does anyone have ideas on what would be a simplified design choice to achieve this?

Thanks a lot

fgaim

@fgaim

@guillaumekln In regards to target side word features (factored MT), the docs for OpenNMT (lua) say the decoder predicts the features of the decoded sentence. So, is the prediction loss being backpropagated along with translation loss, and hence eventually improve both the translation and feature prediction tasks? OR does the translation in any way benefit from target side features in the current implementation? Thanks!

Guillaume Klein

@guillaumekln

is the prediction loss being backpropagated along with translation loss, and hence eventually improve both the translation and feature prediction tasks?

Yes, the losses are summed together before backprogpagation.

stribizhev

@stribizhev

@guillaumekln @jsenellart Is there a way to combine two BPE models? The reason is I have a generic model with its BPE model, then I train an incremental model using new corpora for which I create a new BPE model. When running incremental training, I use -update_vocab merge. If the vocabulary is merged, I guess I should also merge the BPE models to use when translating, right?

Vincent Nguyen

@vince62s

don't create a new bpe model, just tokenize with the first one.

Ayushi Dalmia

@ayushidalmia

Hi, Is there a way to generate the attention map for a given torch model?

hypnoseal

@hypnoseal

Hello, I am interested in learning more about Machine Learning and OpenNMT has me captivated. I have an idea for a project to learn more with OpenNMT, but I require more information on preparing the data source and target files. I've looked through the documentation, but I seem to be having trouble finding any resources about pre-preprocessing the data. As in, are there best practices in preparing the data in source.txt and target.txt before preprocessing? Are there guidelines on the corpus of text required (number of sentences/size of sentences/theme/etc)? Any available reading materials or other resources I could learn more about preparing the data would be greatly appreciated. Thank you very much for the help!

To add to the above question: I plan on using a corpus of text where one body is English and the other is written in Canadian Aboriginal syllabics. Are there considerations I should have with a latin to non-latin characterset? It is possible to convert the syallbics to roman orthography.

Rausch Merscen

@rauschmerscen

@rauschmerscen
Can OpenNMT help me achieve a tool like https://spinbot.com
I have a theory that if I do English->German(or any another language)->English, I can get an article spinner
?

Aditya

@adityakpathak

Hello sir I have question related Audio identification can I use Opennmt for language identification then after language identify coverted into text

It is possible?

Jean Senellart

@jsenellart

@rauschmerscen - the idea is good, but I am not sure it will work since the models are generally trained on same dataset, and EN>DE>EN will be very close to the original. on spinbot they appararently have list of paraphrases they use to generate these alternatives. You can find some good review on paraphrase building and novel approaches here: http://aclweb.org/anthology/E17-1083

Rausch Merscen

@rauschmerscen

@jsenellart Thanks for looking into my project,

Jean Senellart

@jsenellart

@DA1234k - technically it is possible, and we did something like that recently using opennmt-tf (language id on audio signal) - unfortunately we cannot share the paper yet that is in submission. but it is not very hard, you just need data for that

Rausch Merscen

@rauschmerscen

@jsenellart vertu helpful paper

*very

Can you suggest me the easiest way to achieve spinbot, i can't find any repo.

How can I generate/where can i get a list of paraphrases like spin bot has

Saurabh Vyas

@saurabhvyas

Anyone worked with image to markup using open nmt? I am trying to perform inference on a single image using a pretrained model but it currently required whole test set , I dont have labels , just the image

Yuntian

@da03

@saurabhvyas Are you using LuaTorch version or PyTorch version? If it's PyTorch version then no -tgt needs to be provided to translate.py; if it was LuaTorch you can provide dummy ground truth labels such as 'aaa'

stribizhev

@stribizhev

Hi guys, any idea why I am getting

THCudaCheck FAIL file=/tmp/luarocks_cunn-scm-1-1394/cunn/lib/THCUNN/generic/SoftMax.cu line=72 error=48 : no kernel image is available for execution on the device
/torch/install/bin/luajit: /torch/install/share/lua/5.1/nn/THNN.lua:110: cuda runtime error (48) : no kernel image is available for execution on the device at /tmp/luarocks_cunn-scm-1-1394/cunn/lib/THCUNN/generic/SoftMax.cu:72

after [07/06/18 11:09:23 INFO] Preparing memory optimization...? I run training on a Tesla V100 having 4 GPU cores and can't work around this issue. I run training using th ./train.lua ... -gpuid 1 2 3 4.

stribizhev

@stribizhev

Ok, reinstalled Torch, all Luarocks, reboot, tried to install nccl 2.2, udated nn and cunn, and it now runs with CUDA_VISIBLE_DEVICES=0,1,2,3 th ./train.lua ... gpuid 1 2 3 4, but for the life of me, it still says there is no nccl though I installed it from NVIDIA site, both Ubuntu 16.04 normal and S agonstic versions (for CUDA 9.0, though I have CUDA 9.1 installed - but there is no NCCL 9.1 :().

Saurabh Vyas

@saurabhvyas

@da03 thanks for your reply, sorry for late response, it was for lua, and with dummy data is worked nicely, however I am trying pytorch version now, and one tensorflow implementation ( https://github.com/guillaumegenthial/im2latex/ ), in tf version, , I trained with custom font rendering and size augmentation on same formulas.lst provided by im2latex dataset, even though the perplexity training reached 1.07 , and validation perplexity 1.15 ,, almost 80% of the formulas are not exactly matching in test set, should I play with hyperparamters,?

Sirogha

@Sirogha

hi. how i can know - which version cuda used by opennmt?

Guillaume Klein

@guillaumekln

@Sirogha Do you mean the CUDA version that is required by OpenNMT?

M Saiful Bari

@sbmaruf

@guillaumekln hi there...!
In case if two language doesn't share the characters then how do we do the translation on a Name. Like "Rahul" (a male name) is english, should be "راهول" in Arabic, "राहुल" in Hindi.
So how actually <unk> tag replace work in that case.
If there is any related reference paper you can cite that would be great also. And also does OpenNMT supports this?

Guillaume Klein

@guillaumekln

Hi! In OpenNMT-Lua, there is the -phrase_table that can be used for this: for any <unk> token in the target, the corresponding source token is looked up in the table to find a translation. Other approaches include splitting names on characters and let the model learn the translation or, more commonly, replacing entities with placeholder tokens and have a separate processing software to replace these placeholders.

M Saiful Bari

@sbmaruf

Is it also available in openNMT-py/tf?

I don't see any -phrase_table tag for OpenNMT-py

Guillaume Klein

@guillaumekln

Yes it's only in OpenNMT-lua unfortunately but it's not complicated to add in OpenNMT-py. This feature gets less attention nowadays because Transformer models are incompatible with it as it requires alignment information from the model.

M Saiful Bari

@sbmaruf

So if I'm using transformer model there's no way I can solve this?

Guillaume Klein

@guillaumekln

You can try to split them on characters if you believe there are enough examples in the training data for the model to learn something. Otherwise, this requires an external pre- and post- processing.

M Saiful Bari

@sbmaruf

I was thinking about doing some kind of Transliteration/Romanization of the target language to the source language.
Otherwise, this requires an external pre- and post- processing.
what are the pre/post processing? Any resource out there?
Apart from that if I see(in the following link) google translate, see the red marked text here. Is this the pre/post processing steps here?
https://drive.google.com/file/d/1POkH3XE6yfCoNkJn4DyMRP6J11Ecyqjl/view?usp=sharing

Guillaume Klein

@guillaumekln

what are the pre/post processing?

There are several ways to achieve this and I don't know you current workflow for NMT so it's difficult for me to answer.

M Saiful Bari

@sbmaruf

@guillaumekln Thank you for your answer. I will think and work on your points. If I came to any specific problem then I will ask you again. Actually right now I'm exploring NMT. I wanted to see how to handle the different issues of NMT. This is a pedagogical exploration. Right now I don't have any specific workflow. My research goal is to do kind of Discourse exploration in NMT. I just started.

lagleki

@lagleki

does opennmt in tf support attention mechanism?

Jean Senellart

@jsenellart

yes of course

Sirogha

@Sirogha

Hello. If i try to translate some text with -replace_unktagged and -tok{src,tgt}_case_feature, so i get result with ｟unk:xxxxx｠but in only lowercase. How i can find case type for unk?

sergei-from-vironit

@sergei-from-vironit

Hi. I started train data after sentencepiece bpe mode tokenizer. And get error in 4 epoch

[02/08/19 09:43:54 INFO] Epoch 4 ; Iteration 98300/103388 ; Optim SGD LR 1.000000 ; Source tokens/s 8042 ; Perplexity 10.81
/root/torch/install/bin/luajit: bad argument #2 to '?' (out of range at /root/torch/pkg/torch/generic/Tensor.c:913)
stack traceback:
[C]: at 0x7f65146d1580
[C]: in function '__index'
./onmt/train/Trainer.lua:234: in function 'getBatchIdx'
./onmt/train/Trainer.lua:276: in function 'trainEpoch'
./onmt/train/Trainer.lua:484: in function 'train'
train.lua:333: in function 'main'
train.lua:338: in main chunk
[C]: in function 'dofile'
/root/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk
[C]: at 0x00405d50
root@Ubuntu-1604-xenial-64-minimal:~/OpenNMT

What can be do it?

anaskoara

@anaskoara

most NMT models use byte pair encoding for to solve unknow words can anyone explain why it is useful?

@sergei-from-vironit most NMT models use byte pair encoding for to solve unknow words can you explain why it is useful?
_

sahinurlaskar

@sahinurlaskar

Why features are calculated after splitting based on pipe, what if the data does not contain "|"

geekygirl123

@geekygirl123

I have multiple questions regarding copy mechanism implemented in Opennmt toolkit.
1) "Since we are using copy-attention [1] in the model, we need to preprocess the dataset such that source and target are aligned and use the same dictionary. " .This is a line from the readme . What does alignment between source and target words mean?
2) Has anyone tried copy mechanism with transformer architecture? If yes how was the performance?

Guillaume Klein

@guillaumekln

You probably want to post these questions in https://gitter.im/OpenNMT/OpenNMT-py or in the forum https://forum.opennmt.net/

woo chin

@chinwoo987_gitlab

I wonder maybe I should try a different BPE model other the aggressive one? I will try to update more often at https://gitter.im/OpenNMT/OpenNMT-py https://wordcounter.tools

Karen Lastmann Assaraf

@karen.lastmannassaraf_gitlab

Hi!
Did someone already converted an opennmt self attention encoder-decoder to a hugging face transformer?
Thanks!

Where communities thrive

People

Repo info

Activity