Machine Translation Models¶
Machine translation is the task of translating text from one language to another. For example, from English to Spanish. Models are based on the Transformer sequence-to-sequence architecture [nlp-machine_translation4].
An example script on how to train the model can be found here: NeMo/examples/nlp/machine_translation/enc_dec_nmt.py. The default configuration file for the model can be found at: NeMo/examples/nlp/machine_translation/conf/aayn_base.yaml.
Quick Start Guide¶
from nemo.collections.nlp.models import MTEncDecModel
# To get the list of pre-trained models
MTEncDecModel.list_available_models()
# Download and load the a pre-trained to translate from English to Spanish
model = MTEncDecModel.from_pretrained("nmt_en_es_transformer12x2")
# Translate a sentence or list of sentences
translations = model.translate(["Hello!"], source_lang="en", target_lang="es")
Available Models¶
Model |
Pretrained Checkpoint |
---|---|
English -> German |
https://ngc.nvidia.com/catalog/models/nvidia:nemo:nmt_en_de_transformer12x2 |
German -> English |
https://ngc.nvidia.com/catalog/models/nvidia:nemo:nmt_de_en_transformer12x2 |
English -> Spanish |
https://ngc.nvidia.com/catalog/models/nvidia:nemo:nmt_en_es_transformer12x2 |
Spanish -> English |
https://ngc.nvidia.com/catalog/models/nvidia:nemo:nmt_es_en_transformer12x2 |
English -> French |
https://ngc.nvidia.com/catalog/models/nvidia:nemo:nmt_en_fr_transformer12x2 |
French -> English |
https://ngc.nvidia.com/catalog/models/nvidia:nemo:nmt_fr_en_transformer12x2 |
English -> Russian |
https://ngc.nvidia.com/catalog/models/nvidia:nemo:nmt_en_ru_transformer6x6 |
Russian -> English |
https://ngc.nvidia.com/catalog/models/nvidia:nemo:nmt_ru_en_transformer6x6 |
English -> Chinese |
https://ngc.nvidia.com/catalog/models/nvidia:nemo:nmt_en_zh_transformer6x6 |
Chinese -> English |
https://ngc.nvidia.com/catalog/models/nvidia:nemo:nmt_zh_en_transformer6x6 |
Data Format¶
Supervised machine translation models require parallel corpora which comprises many examples of sentences in a source language and their corresponding translation in a target language. We use parallel data formatted as seperate text files for source and target languages where sentences in corresponding files are aligned like in the table below.
train.english.txt |
train.spanish.txt |
---|---|
Hello . |
Hola . |
Thank you . |
Gracias . |
You can now translate from English to Spanish in NeMo . |
Ahora puedes traducir del inglés al español en NeMo . |
It is common practice to apply data cleaning, normalization, and tokenization to the data prior to training a translation model and NeMo expects already cleaned, normalized, and tokenized data. The only data pre-processing NeMo does is subword tokenization with BPE [nlp-machine_translation3].
Data Cleaning, Normalization & Tokenization¶
We recommend applying the following steps to clean, normalize, and tokenize your data. All pre-trained models released, apply these data pre-processing steps.
Language ID filtering - This step filters out examples from your training dataset that aren’t in the correct language. For example, many datasets contain examples where source and target sentences are in the same language. You can use a pre-trained language ID classifier from fastText. You can then run our script using the
lid.176.bin
model downloaded from the fastText website.python NeMo/scripts/neural_machine_translation/filter_by_language.py \ --input-src train.en \ --input-tgt train.es \ --output-src train_lang_filtered.en \ --output-tgt train_lang_filtered.es \ --source-lang en \ --target-lang es \ --removed-src train_noise.en \ --removed-tgt train_noise.de \ --fasttext-model lid.176.bin
Length filtering - We filter out sentences from the data that are below a minimum length (1) or exceed a maximum length (250). We also filter out sentences where the ratio between source and target lengths exceeds 1.3 except for English <-> Chinese models. Moses is a statistical machine translation toolkit that contains many useful pre-processing scripts.
perl mosesdecoder/scripts/training/clean-corpus-n.perl -ratio 1.3 train en es train.filter 1 250
Data cleaning - While language ID filtering can sometimes help with filtering out noisy sentences that contain too many puncutations, it does not help in cases where the translations are potentially incorrect, disfluent, or incomplete. We use bicleaner a tool to identify such sentences. It trains a classifier based on many features included pre-trained language model fluency, word alignment scores from a word-alignment model like Giza++ etc. We use their available pre-trained models wherever possible and train models ourselves using their framework for remaining languages. The following script applies a pre-trained bicleaner model to the data and pick sentences that are clean with probability > 0.5.
awk '{print "-\t-"}' train.en \ | paste -d "\t" - train.filter.en train.filter.es \ | bicleaner-classify - - </path/to/bicleaner.yaml> > train.en-es.bicleaner.score
Data deduplication - We use bifixer (which uses xxHash) to hash the source and target sentences based on which we remove duplicate entries from the file. You may want to do something similar to remove training examples that are in the test dataset.
cat train.en-es.bicleaner.score \ | parallel -j 25 --pipe -k -l 30000 python bifixer.py --ignore-segmentation -q - - en es \ > train.en-es.bifixer.score awk -F awk -F "\t" '!seen[$6]++' train.en-es.bifixer.score > train.en-es.bifixer.dedup.score
Filter out data that bifixer assigns probability < 0.5 to.
awk -F "\t" '{ if ($5>0.5) {print $3}}' train.en-es.bifixer.dedup.score > train.cleaned.en awk -F "\t" '{ if ($5>0.5) {print $4}}' train.en-es.bifixer.dedup.score > train.cleaned.es
Punctuation Normalization - Punctuation, especially things like quotes can be written in different ways. It’s often useful to normalize the way they appear in text. We use the moses punctuation normalizer on all languages except Chinese.
perl mosesdecoder/scripts/tokenizer/normalize-punctuation.perl -l es < train.cleaned.es > train.normalized.es perl mosesdecoder/scripts/tokenizer/normalize-punctuation.perl -l en < train.cleaned.en > train.normalized.en
For example:
Before - Aquí se encuentran joyerías como Tiffany`s entre negocios tradicionales suizos como la confitería Sprüngli. After - Aquí se encuentran joyerías como Tiffany's entre negocios tradicionales suizos como la confitería Sprüngli.
Tokenization and word segmentation for Chinese - Naturally written text often contains punctuation markers like commas, full-stops and apostrophes that are attached to words. Tokenization by just splitting a string on spaces will result in separate token IDs for very similar items like
NeMo
andNeMo.
. Tokenization splits punctuation from the word to create two separate tokens. In the previous exampleNeMo.
becomesNeMo .
which when split by space, results in two tokens and adressess the earlier problem.For example:
Before - Especialmente porque se enfrentará "a Mathieu (Debuchy), Yohan (Cabaye) y Adil (Rami) ", recuerda. After - Especialmente porque se enfrentará " a Mathieu ( Debuchy ) , Yohan ( Cabaye ) y Adil ( Rami ) " , recuerda .
We use the Moses tokenizer for all languages except Chinese.
perl mosesdecoder/scripts/tokenizer/tokenizer.perl -l es -no-escape < train.normalized.es > train.tokenized.es perl mosesdecoder/scripts/tokenizer/tokenizer.perl -l en -no-escape < train.normalized.en > train.tokenized.en
For languages like Chinese where there is no explicit marker like spaces that separate words, we use Jieba to segment a string into words that are space separated.
For example:
Before - 同时,卫生局认为有必要接种的其他人员,包括公共部门,卫生局将主动联络有关机构取得名单后由卫生中心安排接种。 After - 同时 , 卫生局 认为 有 必要 接种 的 其他 人员 , 包括 公共部门 , 卫生局 将 主动 联络 有关 机构 取得 名单 后 由 卫生 中心 安排 接种 。
Training a BPE Tokenization¶
Byte-pair encoding (BPE) [nlp-machine_translation3] is a sub-word tokenization algorithm that is commonly used to reduce the large vocabulary size of datasets by splitting words into frequently occuring sub-words. Currently, mMachine translation only supports the YouTokenToMe BPE tokenizer. One can set the tokenization configuration as follows:
Parameter |
Data Type |
Default |
Description |
model.{encoder_tokenizer,decoder_tokenizer}.tokenizer_name |
str |
|
BPE library name. Only supports |
model.{encoder_tokenizer,decoder_tokenizer}.tokenizer_model |
str |
|
Path to an existing YTTM BPE model. If |
model.{encoder_tokenizer,decoder_tokenizer}.vocab_size |
int |
|
Desired vocabulary size after BPE tokenization. |
model.{encoder_tokenizer,decoder_tokenizer}.bpe_dropout |
float |
|
BPE dropout probability. [nlp-machine_translation2]. |
model.{encoder_tokenizer,decoder_tokenizer}.vocab_file |
str |
|
Path to pre-computed vocab file if exists. |
model.shared_tokenizer |
bool |
|
Whether to share the tokenizer between the encoder and decoder. |
Applying BPE Tokenization, Batching, Bucketing and Padding¶
Given BPE tokenizers, and a cleaned parallel corpus, the following steps are applied to create a TranslationDataset object.
Text to IDs - This performs subword tokenization with the BPE model on an input string and maps it to a sequence of tokens for the source and target text.
Bucketing - Sentences vary in length and when creating minibatches, we’d like sentences in them to have roughly the same length to minimize the number of
<pad>
tokens and to maximize computational efficiency. This step groups sentences roughly the same length into buckets.Batching and padding - Creates minibatches with a maximum number of tokens specified by
model.{train_ds,validation_ds,test_ds}.tokens_in_batch
from buckets and pads, so they can be packed into a tensor.
Datasets can be configured as follows:
Parameter |
Data Type |
Default |
Description |
model.{train_ds,validation_ds,test_ds}.src_file_name |
str |
|
Path to the source language file. |
model.{train_ds,validation_ds,test_ds}.tgt_file_name |
str |
|
Path to the target language file. |
model.{train_ds,validation_ds,test_ds}.tokens_in_batch |
int |
|
Maximum number of tokens per minibatch. |
model.{train_ds,validation_ds,test_ds}.clean |
bool |
|
Whether to clean the dataset by discarding examples that are greater than |
model.{train_ds,validation_ds,test_ds}.max_seq_length |
int |
|
Maximum sequence to be used with the |
model.{train_ds,validation_ds,test_ds}.shuffle |
bool |
|
Whether to shuffle minibatches in the PyTorch DataLoader. |
model.{train_ds,validation_ds,test_ds}.num_samples |
int |
|
Number of samples to use. |
model.{train_ds,validation_ds,test_ds}.drop_last |
bool |
|
Drop last minibatch if it is not of equal size to the others. |
model.{train_ds,validation_ds,test_ds}.pin_memory |
bool |
|
Whether to pin memory in the PyTorch DataLoader. |
model.{train_ds,validation_ds,test_ds}.num_workers |
int |
|
Number of workers for the PyTorch DataLoader. |
Tarred Datasets for Large Corpora¶
When training with DistributedDataParallel
, each process has its own copy of the dataset. For large datasets, this may not always
fit in CPU memory. Webdatasets circumvents this problem by efficiently iterating over
tar files stored on disk. Each tar file can contain hundreds to thousands of pickle files, each containing a single minibatch.
We recommend using this method when working with datasets with > 1 million sentence pairs.
Tarred datasets can be configured as follows:
Parameter |
Data Type |
Default |
Description |
model.{train_ds,validation_ds,test_ds}.use_tarred_dataset |
bool |
|
Whether to use tarred datasets. |
model.{train_ds,validation_ds,test_ds}.tar_files |
str |
|
String specifying path to all tar files. Example with 100 tarfiles |
model.{train_ds,validation_ds,test_ds}.metadata_file |
str |
|
Path to JSON metadata file that contains only a single entry for the total number of batches in the dataset. |
model.{train_ds,validation_ds,test_ds}.lines_per_dataset_fragment |
int |
|
|
model.{train_ds,validation_ds,test_ds}.num_batches_per_tarfile |
int |
|
Maximum sequence to be used with the |
model.{train_ds,validation_ds,test_ds}.tar_shuffle_n |
int |
|
Whether to cache IDs to avoid re-tokenizing data. This will be deprecated in favor of tarred datasets. |
model.{train_ds,validation_ds,test_ds}.shard_strategy |
str |
|
Whether to cache IDs in each of the nodes in multi-node training. |
model.preproc_out_dir |
str |
|
Path to folder that contains processed tar files or directory where new tar files are written. |
Tarred datasets can be created in two ways:
Using the Hydra config and training script.
For example:
python examples/nlp/machine_translation/enc_dec_nmt.py \ -cn aayn_base \ do_training=false \ model.preproc_out_dir=/path/to/preproc_dir \ model.train_ds.use_tarred_dataset=true \ model.train_ds.lines_per_dataset_fragment=1000000 \ model.train_ds.num_batches_per_tarfile=200 \ model.train_ds.src_file_name=train.tokenized.en \ model.train_ds.tgt_file_name=train.tokenized.es \ model.validation_ds.src_file_name=validation.tokenized.en \ model.validation_ds.tgt_file_name=validation.tokenized.es \ model.encoder_tokenizer.vocab_size=32000 \ model.decoder_tokenizer.vocab_size=32000 \ ~model.test_ds \ trainer.gpus=[0,1,2,3] \ +trainer.fast_dev_run=true \ exp_manager=null \
The above script processes the parallel tokenized text files into tarred datasets that are written to
/path/to/preproc_dir
. Sincedo_training
is set toFalse
, the above script only creates tarred datasets and then exits. Ifdo_training
is setTrue
, then one of two things happen:If no tar files are present in
model.preproc_out_dir
, the script first creates those files and then commences training.If tar files are already present in
model.preproc_out_dir
, the script starts training from the provided tar files.
Using a separate script without Hydra.
Tarred datasets for parallel corpora can also be created with a script that doesn’t require specifying a configs via Hydra and just uses Python argparse.
For example:
python examples/nlp/machine_translation/create_tarred_parallel_dataset.py \ --shared_tokenizer \ --clean \ --bpe_dropout 0.1 \ --src_fname train.tokenized.en \ --tgt_fname train.tokenized.es \ --out_dir /path/to/preproc_dir \ --vocab_size 32000 \ --max_seq_length 512 \ --min_seq_length 1 \ --tokens_in_batch 8192 \ --lines_per_dataset_fragment 1000000 \ --num_batches_per_tarfile 200
You can then set model.preproc_out_dir=/path/to/preproc_dir and model.train_ds.use_tarred_dataset=true to train with this data.
Model Configuration and Training¶
The overall model consists of an encoder, decoder, and classification head. Encoders and decoders have the following configuration options:
Parameter |
Data Type |
Default |
Description |
model.{encoder,decoder}.max_sequence_length |
int |
|
Maximum sequence length of positional encodings. |
model.{encoder,decoder}.embedding_dropout |
float |
|
Path to JSON metadata file that contains only a single entry for the total number of batches in the dataset. |
model.{encoder,decoder}.learn_positional_encodings |
bool |
|
If |
model.{encoder,decoder}.hidden_size |
int |
|
Size of the transformer hidden states. |
model.{encoder,decoder}.num_layers |
int |
|
Number of transformer layers. |
model.{encoder,decoder}.inner_size |
int |
|
Size of the hidden states within the feedforward layers. |
model.{encoder,decoder}.num_attention_heads |
int |
|
Number of attention heads. |
model.{encoder,decoder}.ffn_dropout |
float |
|
Dropout probability within the feedforward layers. |
model.{encoder,decoder}.attn_score_dropout |
float |
|
Dropout probability of the attention scores before softmax normalization. |
model.{encoder,decoder}.attn_layer_dropout |
float |
|
Dropout probability of the attention query, key, and value projection activations. |
model.{encoder,decoder}.hidden_act |
str |
|
Activation function throughout the network. |
model.{encoder,decoder}.mask_future |
bool |
|
Whether to mask future timesteps for attention. Defaults to |
model.{encoder,decoder}.pre_ln |
bool |
|
Whether to apply layer-normalization before ( |
Our pre-trained models are optimized with Adam, with a maximum learning of 0.0004, beta of (0.9, 0.98), an inverse square root learning rate schedule from [nlp-machine_translation4]. The model.optim section sets the optimization parameters.
The following script creates tarred datasets based on the provided parallel corpus and train a model based on the base
configuration
from [nlp-machine_translation4].
python examples/nlp/machine_translation/enc_dec_nmt.py \
-cn aayn_base \
do_training=true \
trainer.gpus=8 \
~trainer.max_epochs \
+trainer.max_steps=100000 \
+trainer.val_check_interval=1000 \
+exp_manager.exp_dir=/path/to/store/results \
+exp_manager.create_checkpoint_callback=True \
+exp_manager.checkpoint_callback_params.monitor=val_sacreBLEU \
+exp_manager.checkpoint_callback_params.mode=max \
+exp_manager.checkpoint_callback_params.save_top_k=5 \
model.preproc_out_dir=/path/to/preproc_dir \
model.train_ds.use_tarred_dataset=true \
model.train_ds.lines_per_dataset_fragment=1000000 \
model.train_ds.num_batches_per_tarfile=200 \
model.train_ds.src_file_name=train.tokenized.en \
model.train_ds.tgt_file_name=train.tokenized.es \
model.validation_ds.src_file_name=validation.tokenized.en \
model.validation_ds.tgt_file_name=validation.tokenized.es \
model.encoder_tokenizer.vocab_size=32000 \
model.decoder_tokenizer.vocab_size=32000 \
~model.test_ds \
The trainer keeps track of the sacreBLEU score [nlp-machine_translation1] on the provided validation set and saves the checkpoints that had the top 5 (by default) sacreBLEU scores.
At the end of training, a .nemo
file is written to the result directory which allows to run inference on a test set.
Multi-Validation¶
To run validation on multiple datasets, specify validation_ds.src_file_name
and validation_ds.tgt_file_name
with a list of file paths:
model.validation_ds.src_file_name=[/data/wmt13-en-de.src,/data/wmt14-en-de.src] \
model.validation_ds.tgt_file_name=[/data/wmt13-en-de.ref,/data/wmt14-en-de.ref] \
When using val_loss
or val_sacreBLEU
for the exp_manager.checkpoint_callback_params.monitor
then the 0th indexed dataset will be used as the monitor.
To use other indexes, append the index:
exp_manager.checkpoint_callback_params.monitor=val_sacreBLEU_dl_index_1
Multiple test datasets work exactly the same way as validation datasets, simply replace validation_ds
by test_ds
in the above examples.
Model Inference¶
To generate translations on a test set and compute sacreBLEU scores, run the inference script:
python examples/nlp/machine_translation/nmt_transformer_infer.py \
--model /path/to/model.nemo \
--srctext test.en \
--tgtout test.en-es.translations \
--batch_size 128 \
--source_lang en \
--target_lang es
The --srctext
file must be provided before tokenization and normalization. The resulting --tgtout
file is detokenized and
can be used to compute sacreBLEU scores.
cat test.en-es.translations | sacrebleu test.es
References¶
- nlp-machine_translation1
Matt Post. A call for clarity in reporting bleu scores. arXiv preprint arXiv:1804.08771, 2018.
- nlp-machine_translation2
Ivan Provilkov, Dmitrii Emelianenko, and Elena Voita. Bpe-dropout: simple and effective subword regularization. arXiv preprint arXiv:1910.13267, 2019.
- nlp-machine_translation3(1,2)
Rico Sennrich, Barry Haddow, and Alexandra Birch. Neural machine translation of rare words with subword units. arXiv preprint arXiv:1508.07909, 2015.
- nlp-machine_translation4(1,2,3)
Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. Attention is all you need. arXiv preprint arXiv:1706.03762, 2017.