Deeply Supervised, Layer-wise Prediction-aware (DSLP) Transformer for Non-autoregressive Neural Machine Translation

Non-Autoregressive Translation with Layer-Wise Prediction and Deep Supervision

Training Efficiency

We show the training efficiency of our DSLP model based on vanilla NAT model. Specifically, we compared the BLUE socres of vanilla NAT and vanilla NAT with DSLP & Mixed Training on the same traning time (in hours).

As we observed, our DSLP model achieves much higher BLUE scores shortly after the training started (~3 hours). It shows that our DSLP is much more efficient in training, as our model ahieves higher BLUE scores with the same amount of training cost.

We run the experiments with 8 Tesla V100 GPUs. The batch size is 128K tokens, and each model is trained with 300K updates.

Replication

We provide the scripts of replicating the results on WMT'14 EN-DE task.

Dataset

We download the distilled data from FairSeq

Preprocessed by

TEXT=wmt14_ende_distill
python3 fairseq_cli/preprocess.py --source-lang en --target-lang de \
   --trainpref $TEXT/train.en-de --validpref $TEXT/valid.en-de --testpref $TEXT/test.en-de \
   --destdir data-bin/wmt14.en-de_kd --workers 40 --joined-dictionary

Training:

GLAT with DSLP

python3 train.py data-bin/wmt14.en-de_kd --source-lang en --target-lang de  --save-dir checkpoints  --eval-tokenized-bleu \
   --keep-interval-updates 5 --save-interval-updates 500 --validate-interval-updates 500 --maximize-best-checkpoint-metric \
   --eval-bleu-remove-bpe --eval-bleu-print-samples --best-checkpoint-metric bleu --log-format simple --log-interval 100 \
   --eval-bleu --eval-bleu-detok space --keep-last-epochs 5 --keep-best-checkpoints 5  --fixed-validation-seed 7 --ddp-backend=no_c10d \
   --share-all-embeddings --decoder-learned-pos --encoder-learned-pos  --optimizer adam --adam-betas "(0.9,0.98)" --lr 0.0005 \ 
   --lr-scheduler inverse_sqrt --stop-min-lr 1e-09 --warmup-updates 10000 --warmup-init-lr 1e-07 --apply-bert-init --weight-decay 0.01 \
   --fp16 --clip-norm 2.0 --max-update 300000  --task translation_glat --criterion glat_loss --arch glat_sd --noise full_mask \ 
   --src-upsample-scale 2 --use-ctc-decoder --ctc-beam-size 1  --concat-yhat --concat-dropout 0.0  --label-smoothing 0.1 \ 
   --activation-fn gelu --dropout 0.1  --max-tokens 8192 --glat-mode glat

CMLM with DSLP

python3 train.py data-bin/wmt14.en-de_kd --source-lang en --target-lang de  --save-dir checkpoints  --eval-tokenized-bleu \
   --keep-interval-updates 5 --save-interval-updates 500 --validate-interval-updates 500 --maximize-best-checkpoint-metric \
   --eval-bleu-remove-bpe --eval-bleu-print-samples --best-checkpoint-metric bleu --log-format simple --log-interval 100 \
   --eval-bleu --eval-bleu-detok space --keep-last-epochs 5 --keep-best-checkpoints 5  --fixed-validation-seed 7 --ddp-backend=no_c10d \
   --share-all-embeddings --decoder-learned-pos --encoder-learned-pos  --optimizer adam --adam-betas "(0.9,0.98)" --lr 0.0005 \ 
   --lr-scheduler inverse_sqrt --stop-min-lr 1e-09 --warmup-updates 10000 --warmup-init-lr 1e-07 --apply-bert-init --weight-decay 0.01 \
   --fp16 --clip-norm 2.0 --max-update 300000  --task translation_lev --criterion nat_loss --arch glat_sd --noise full_mask \ 
   --src-upsample-scale 2 --use-ctc-decoder --ctc-beam-size 1  --concat-yhat --concat-dropout 0.0  --label-smoothing 0.1 \ 
   --activation-fn gelu --dropout 0.1  --max-tokens 8192

Vanilla NAT with DSLP

python3 train.py data-bin/wmt14.en-de_kd --source-lang en --target-lang de  --save-dir checkpoints  --eval-tokenized-bleu \
   --keep-interval-updates 5 --save-interval-updates 500 --validate-interval-updates 500 --maximize-best-checkpoint-metric \
   --eval-bleu-remove-bpe --eval-bleu-print-samples --best-checkpoint-metric bleu --log-format simple --log-interval 100 \
   --eval-bleu --eval-bleu-detok space --keep-last-epochs 5 --keep-best-checkpoints 5  --fixed-validation-seed 7 --ddp-backend=no_c10d \
   --share-all-embeddings --decoder-learned-pos --encoder-learned-pos  --optimizer adam --adam-betas "(0.9,0.98)" --lr 0.0005 \ 
   --lr-scheduler inverse_sqrt --stop-min-lr 1e-09 --warmup-updates 10000 --warmup-init-lr 1e-07 --apply-bert-init --weight-decay 0.01 \
   --fp16 --clip-norm 2.0 --max-update 300000  --task translation_lev --criterion nat_loss --arch nat_sd --noise full_mask \ 
   --src-upsample-scale 2 --use-ctc-decoder --ctc-beam-size 1  --concat-yhat --concat-dropout 0.0  --label-smoothing 0.1 \ 
   --activation-fn gelu --dropout 0.1  --max-tokens 8192

Vanilla NAT with DSLP and Mixed Training:

python3 train.py data-bin/wmt14.en-de_kd --source-lang en --target-lang de  --save-dir checkpoints  --eval-tokenized-bleu \
   --keep-interval-updates 5 --save-interval-updates 500 --validate-interval-updates 500 --maximize-best-checkpoint-metric \
   --eval-bleu-remove-bpe --eval-bleu-print-samples --best-checkpoint-metric bleu --log-format simple --log-interval 100 \
   --eval-bleu --eval-bleu-detok space --keep-last-epochs 5 --keep-best-checkpoints 5  --fixed-validation-seed 7 --ddp-backend=no_c10d \
   --share-all-embeddings --decoder-learned-pos --encoder-learned-pos  --optimizer adam --adam-betas "(0.9,0.98)" --lr 0.0005 \ 
   --lr-scheduler inverse_sqrt --stop-min-lr 1e-09 --warmup-updates 10000 --warmup-init-lr 1e-07 --apply-bert-init --weight-decay 0.01 \
   --fp16 --clip-norm 2.0 --max-update 300000  --task translation_lev --criterion nat_loss --arch nat_sd --noise full_mask \ 
   --src-upsample-scale 2 --use-ctc-decoder --ctc-beam-size 1  --concat-yhat --concat-dropout 0.0  --label-smoothing 0.1 \ 
   --activation-fn gelu --dropout 0.1  --max-tokens 8192  --ss-ratio 0.3 --fixed-ss-ratio --masked-loss

CTC with DSLP:

python3 train.py data-bin/wmt14.en-de_kd --source-lang en --target-lang de  --save-dir checkpoints  --eval-tokenized-bleu \
   --keep-interval-updates 5 --save-interval-updates 500 --validate-interval-updates 500 --maximize-best-checkpoint-metric \
   --eval-bleu-remove-bpe --eval-bleu-print-samples --best-checkpoint-metric bleu --log-format simple --log-interval 100 \
   --eval-bleu --eval-bleu-detok space --keep-last-epochs 5 --keep-best-checkpoints 5  --fixed-validation-seed 7 --ddp-backend=no_c10d \
   --share-all-embeddings --decoder-learned-pos --encoder-learned-pos  --optimizer adam --adam-betas "(0.9,0.98)" --lr 0.0005 \ 
   --lr-scheduler inverse_sqrt --stop-min-lr 1e-09 --warmup-updates 10000 --warmup-init-lr 1e-07 --apply-bert-init --weight-decay 0.01 \
   --fp16 --clip-norm 2.0 --max-update 300000  --task translation_lev --criterion nat_loss --arch nat_ctc_sd --noise full_mask \ 
   --src-upsample-scale 2 --use-ctc-decoder --ctc-beam-size 1  --concat-yhat --concat-dropout 0.0  \ 
   --activation-fn gelu --dropout 0.1  --max-tokens 8192

CTC with DSLP and Mixed Training:

python3 train.py data-bin/wmt14.en-de_kd --source-lang en --target-lang de  --save-dir checkpoints  --eval-tokenized-bleu \
   --keep-interval-updates 5 --save-interval-updates 500 --validate-interval-updates 500 --maximize-best-checkpoint-metric \
   --eval-bleu-remove-bpe --eval-bleu-print-samples --best-checkpoint-metric bleu --log-format simple --log-interval 100 \
   --eval-bleu --eval-bleu-detok space --keep-last-epochs 5 --keep-best-checkpoints 5  --fixed-validation-seed 7 --ddp-backend=no_c10d \
   --share-all-embeddings --decoder-learned-pos --encoder-learned-pos  --optimizer adam --adam-betas "(0.9,0.98)" --lr 0.0005 \ 
   --lr-scheduler inverse_sqrt --stop-min-lr 1e-09 --warmup-updates 10000 --warmup-init-lr 1e-07 --apply-bert-init --weight-decay 0.01 \
   --fp16 --clip-norm 2.0 --max-update 300000  --task translation_lev --criterion nat_loss --arch nat_ctc_sd_ss --noise full_mask \ 
   --src-upsample-scale 2 --use-ctc-decoder --ctc-beam-size 1  --concat-yhat --concat-dropout 0.0  \ 
   --activation-fn gelu --dropout 0.1  --max-tokens 8192 --ss-ratio 0.3 --fixed-ss-ratio

Evaluation

fairseq-generate data-bin/wmt14.en-de_kd  --path PATH_TO_A_CHECKPOINT \
    --gen-subset test --task translation_lev --iter-decode-max-iter 0 \
    --iter-decode-eos-penalty 0 --beam 1 --remove-bpe --print-step --batch-size 100

Note: 1) Add --plain-ctc --model-overrides '{"ctc_beam_size": 1, "plain_ctc": True}' if it is CTC based; 2) Change the task to translation_glat if it is GLAT based.

Output

We in addition provide the output of CTC w/ DSLP, CTC w/ DSLP & Mixed Training, Vanilla NAT w/ DSLP, Vanilla NAT w/ DSLP with Mixed Training, GLAT w/ DSLP, and CMLM w/ DSLP for review purpose.

Model	Reference	Hypothesis
CTC w/ DSLP	ref	hyp
CTC w/ DSLP & Mixed Training	ref	hyp
Vanilla NAT w/ DSLP	ref	hyp
Vanilla NAT w/ DSLP & Mixed Training	ref	hyp
GLAT w/ DSLP	ref	hyp
CMLM w/ DSLP	ref	hyp

Note: The output is on WMT'14 EN-DE. The references are paired with hypotheses for each model.

Deeply Supervised, Layer-wise Prediction-aware (DSLP) Transformer for Non-autoregressive Neural Machine Translation

Related tags

Overview

Training Efficiency

Replication

Dataset

Training:

Evaluation

Output

Owner

Chenyang Huang

Optimizaciones incrementales al problema N-Body con el fin de evaluar y comparar las prestaciones de los traductores de Python en el ámbito de HPC.

Official code for ICCV2021 paper "M3D-VTON: A Monocular-to-3D Virtual Try-on Network"

Classifying audio using Wavelet transform and deep learning

A method to perform unsupervised cross-region adaptation of crop classifiers trained with satellite image time series.

An image base contains 490 images for learning (400 cars and 90 boats), and another 21 images for testingAn image base contains 490 images for learning (400 cars and 90 boats), and another 21 images for testing

Source-to-Source Debuggable Derivatives in Pure Python

A curated list of awesome game datasets, and tools to artificial intelligence in games

Datasets, Transforms and Models specific to Computer Vision

AIR^2 for Interaction Prediction

Keras code and weights files for popular deep learning models.

Continuous Diffusion Graph Neural Network

Behavioral "black-box" testing for recommender systems

DISTIL: Deep dIverSified inTeractIve Learning.

Dense Unsupervised Learning for Video Segmentation (NeurIPS*2021)

Product-based-recommendation-system - A product based recommendation system which uses Machine learning algorithm such as KNN and cosine similarity

Implementation of the algorithm shown in the article "Modelo de Predicción de Éxito de Canciones Basado en Descriptores de Audio"

CRNN With PyTorch

Implementation for Panoptic-PolarNet (CVPR 2021)

Convert Pytorch model to onnx or tflite, and the converted model can be visualized by Netron

Partial implementation of ODE-GAN technique from the paper Training Generative Adversarial Networks by Solving Ordinary Differential Equations