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

Overview

This repo contains the implementation of our paper:

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

Paper Link

Replication

Python environment

pip install -e . # under DSLP directory
pip install tensorflow tensorboard sacremoses nltk Ninja omegaconf
pip install 'fuzzywuzzy[speedup]'
pip install hydra-core==1.0.6
pip install sacrebleu==1.5.1
pip install git+https://github.com/dugu9sword/lunanlp.git
git clone --recursive https://github.com/parlance/ctcdecode.git
cd ctcdecode && pip install .

Dataset

We downloaded 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

Or you can download all the binarized files here.

Hyperparameters

EN<->RO EN<->DE
--validate-interval-updates 300 500
number of tokens per batch 32K 128K
--dropout 0.3 0.1

Note:

  1. We found that label smoothing for CTC-based models are not useful (at least not with our implementation), it is suggested to keep --label-smoothing as 0 for them.
  2. Dropout rate plays a significant role for GLAT, CMLM, and the Vanilla NAT. On WMT'14 EN->De, for example, the Vanilla NAT with dropout 0.1 reaches 21.18 BLEU; but only gives 19.68 BLEU with dropout 0.3.

Training:

We provide the scripts for replicating the results on WMT'14 EN->DE task. For other tasks, you need to adapt the binary path, --source-lang, --target-lang, and some other hyperparameters accordingly.

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 \ 
   --concat-yhat --concat-dropout 0.0  --label-smoothing 0.1 \ 
   --activation-fn gelu --dropout 0.1  --max-tokens 8192 --glat-mode glat \ 
   --length-loss-factor 0.1 --pred-length-offset 

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 \ 
   --concat-yhat --concat-dropout 0.0  --label-smoothing 0.1 \ 
   --activation-fn gelu --dropout 0.1  --max-tokens 8192 \
   --length-loss-factor 0.1 --pred-length-offset 

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 \ 
   --concat-yhat --concat-dropout 0.0  --label-smoothing 0.1 \ 
   --activation-fn gelu --dropout 0.1  --max-tokens 8192 \
   --length-loss-factor 0.1 --pred-length-offset 

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 \ 
   --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 \ 
   --length-loss-factor 0.1 --pred-length-offset 

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  --label-smoothing 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  --label-smoothing 0.0 \ 
   --activation-fn gelu --dropout 0.1  --max-tokens 8192 --ss-ratio 0.3 --fixed-ss-ratio

Evaluation

Average the last best 5 checkpoints with scripts/average_checkpoints.py, our results are based on either the best checkpoint or the averaged checkpoint, depending on their valid set BLEU.

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.

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.

Efficiency

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

Owner
Chenyang Huang
Stay hungry, stay foolish
Chenyang Huang
Implementation of Natural Language Code Search in the project CodeBERT: A Pre-Trained Model for Programming and Natural Languages.

CodeBERT-Implementation In this repo we have replicated the paper CodeBERT: A Pre-Trained Model for Programming and Natural Languages. We are interest

Tanuj Sur 4 Jul 01, 2022
NLP tool to extract emotional phrase from tweets 🤩

Emotional phrase extractor Extract phrase in the given text that is used to express the sentiment. Capturing sentiment in language is important in the

Shahul ES 38 Oct 17, 2022
DELTA is a deep learning based natural language and speech processing platform.

DELTA - A DEep learning Language Technology plAtform What is DELTA? DELTA is a deep learning based end-to-end natural language and speech processing p

DELTA 1.5k Dec 26, 2022
Implementation of Token Shift GPT - An autoregressive model that solely relies on shifting the sequence space for mixing

Token Shift GPT Implementation of Token Shift GPT - An autoregressive model that relies solely on shifting along the sequence dimension and feedforwar

Phil Wang 32 Oct 14, 2022
Toolkit for Machine Learning, Natural Language Processing, and Text Generation, in TensorFlow. This is part of the CASL project: http://casl-project.ai/

Texar is a toolkit aiming to support a broad set of machine learning, especially natural language processing and text generation tasks. Texar provides

ASYML 2.3k Jan 07, 2023
Visual Automata is a Python 3 library built as a wrapper for Caleb Evans' Automata library to add more visualization features.

Visual Automata Copyright 2021 Lewi Lie Uberg Released under the MIT license Visual Automata is a Python 3 library built as a wrapper for Caleb Evans'

Lewi Uberg 55 Nov 17, 2022
Learning to Rewrite for Non-Autoregressive Neural Machine Translation

RewriteNAT This repo provides the code for reproducing our proposed RewriteNAT in EMNLP 2021 paper entitled "Learning to Rewrite for Non-Autoregressiv

Xinwei Geng 20 Dec 25, 2022
Grover is a model for Neural Fake News -- both generation and detectio

Grover is a model for Neural Fake News -- both generation and detection. However, it probably can also be used for other generation tasks.

Rowan Zellers 856 Dec 24, 2022
This is the code for the EMNLP 2021 paper AEDA: An Easier Data Augmentation Technique for Text Classification

The baseline code is for EDA: Easy Data Augmentation techniques for boosting performance on text classification tasks

Akbar Karimi 81 Dec 09, 2022
A natural language processing model for sequential sentence classification in medical abstracts.

NLP PubMed Medical Research Paper Abstract (Randomized Controlled Trial) A natural language processing model for sequential sentence classification in

Hemanth Chandran 1 Jan 17, 2022
Simple Annotated implementation of GPT-NeoX in PyTorch

Simple Annotated implementation of GPT-NeoX in PyTorch This is a simpler implementation of GPT-NeoX in PyTorch. We have taken out several optimization

labml.ai 101 Dec 03, 2022
Lingtrain Aligner — ML powered library for the accurate texts alignment.

Lingtrain Aligner ML powered library for the accurate texts alignment in different languages. Purpose Main purpose of this alignment tool is to build

Sergei Averkiev 76 Dec 14, 2022
A sample project that exists for PyPUG's "Tutorial on Packaging and Distributing Projects"

A sample Python project A sample project that exists as an aid to the Python Packaging User Guide's Tutorial on Packaging and Distributing Projects. T

Python Packaging Authority 4.5k Dec 30, 2022
C.J. Hutto 3.8k Dec 30, 2022
This is Assignment1 code for the Web Data Processing System.

This is a Python program to Entity Linking by processing WARC files. We recognize entities from web pages and link them to a Knowledge Base(Wikidata).

3 Dec 04, 2022
CorNet Correlation Networks for Extreme Multi-label Text Classification

CorNet Correlation Networks for Extreme Multi-label Text Classification Prerequisites python==3.6.3 pytorch==1.2.0 torchgpipe==0.0.5 click==7.0 ruamel

Guangxu Xun 38 Dec 31, 2022
A unified tokenization tool for Images, Chinese and English.

ICE Tokenizer Token id [0, 20000) are image tokens. Token id [20000, 20100) are common tokens, mainly punctuations. E.g., icetk[20000] == 'unk', ice

THUDM 42 Dec 27, 2022
Practical Natural Language Processing Tools for Humans is build on the top of Senna Natural Language Processing (NLP)

Practical Natural Language Processing Tools for Humans is build on the top of Senna Natural Language Processing (NLP) predictions: part-of-speech (POS) tags, chunking (CHK), name entity recognition (

jawahar 20 Apr 30, 2022
Bidirectional Variational Inference for Non-Autoregressive Text-to-Speech (BVAE-TTS)

Bidirectional Variational Inference for Non-Autoregressive Text-to-Speech (BVAE-TTS) Yoonhyung Lee, Joongbo Shin, Kyomin Jung Abstract: Although early

LEE YOON HYUNG 147 Dec 05, 2022
A combination of autoregressors and autoencoders using XLNet for sentiment analysis

A combination of autoregressors and autoencoders using XLNet for sentiment analysis Abstract In this paper sentiment analysis has been performed in or

James Zaridis 2 Nov 20, 2021