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

Open-Source Toolkit for End-to-End Speech Recognition leveraging PyTorch-Lightning and Hydra.

Healthsea is a spaCy pipeline for analyzing user reviews of supplementary products for their effects on health.

BARTpho: Pre-trained Sequence-to-Sequence Models for Vietnamese

Yet Another Sequence Encoder - Encode sequences to vector of vector in python !

Implementation of Fast Transformer in Pytorch

A repository to run gpt-j-6b on low vram machines (4.2 gb minimum vram for 2000 token context, 3.5 gb for 1000 token context). Model loading takes 12gb free ram.

Multi-Scale Temporal Frequency Convolutional Network With Axial Attention for Speech Enhancement

Athena is an open-source implementation of end-to-end speech processing engine.

Implementation of Multistream Transformers in Pytorch

Sorce code and datasets for "K-BERT: Enabling Language Representation with Knowledge Graph",

Translate - a PyTorch Language Library

Knowledge Graph,Question Answering System，基于知识图谱和向量检索的医疗诊断问答系统

Tools to download and cleanup Common Crawl data

문장단위로 분절된 나무위키 데이터셋. Releases에서 다운로드 받거나, tfds-korean을 통해 다운로드 받으세요.

An implementation of model parallel GPT-3-like models on GPUs, based on the DeepSpeed library. Designed to be able to train models in the hundreds of billions of parameters or larger.

Repository for Graph2Pix: A Graph-Based Image to Image Translation Framework

Header-only C++ HNSW implementation with python bindings

Signature remover is a NLP based solution which removes email signatures from the rest of the text.

ConvBERT: Improving BERT with Span-based Dynamic Convolution

Awesome Treasure of Transformers Models Collection