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

Code for PED: DETR For (Crowd) Pedestrian Detection

An easy to use Natural Language Processing library and framework for predicting, training, fine-tuning, and serving up state-of-the-art NLP models.

Implementing SimCSE(paper, official repository) using TensorFlow 2 and KR-BERT.

This is the Alpha of Nutte language, she is not complete yet / Essa é a Alpha da Nutte language, não está completa ainda

StarGAN - Official PyTorch Implementation

Code for lyric-section-to-comment generation based on huggingface transformers.

Translators - is a library which aims to bring free, multiple, enjoyable translation to individuals and students in Python

STS Benchmark comprises a selection of the English datasets used in the STS tasks organized in the context of SemEval between 2012 and 2017. The selection of datasets include text from image captions, news headlines and user forums.

Estimation of the CEFR complexity score of a given word, sentence or text.

Sequence model architectures from scratch in PyTorch

Python bot created with Selenium that can guess the daily Wordle word correct 96.8% of the time.

Code repository of the paper Neural circuit policies enabling auditable autonomy published in Nature Machine Intelligence

CCQA A New Web-Scale Question Answering Dataset for Model Pre-Training

Various capabilities for static malware analysis.

neural network based speaker embedder

A deep learning-based translation library built on Huggingface transformers

Resources for "Natural Language Processing" Coursera course.

AI-powered literature discovery and review engine for medical/scientific papers

Guide to using pre-trained large language models of source code

Chinese real time voice cloning (VC) and Chinese text to speech (TTS).