Sequence-to-Sequence learning using PyTorch

Last update: Nov 17, 2022

Overview

Seq2Seq in PyTorch

This is a complete suite for training sequence-to-sequence models in PyTorch. It consists of several models and code to both train and infer using them.

Using this code you can train:

Neural-machine-translation (NMT) models
Language models
Image to caption generation
Skip-thought sentence representations
And more...

Installation

git clone --recursive https://github.com/eladhoffer/seq2seq.pytorch
cd seq2seq.pytorch; python setup.py develop

Models

Models currently available:

Simple Seq2Seq recurrent model
Recurrent Seq2Seq with attentional decoder
Google neural machine translation (GNMT) recurrent model
Transformer - attention-only model from "Attention Is All You Need"

Datasets

Datasets currently available:

WMT16
WMT17
OpenSubtitles 2016
COCO image captions
Conceptual captions

All datasets can be tokenized using 3 available segmentation methods:

Character based segmentation
Word based segmentation
Byte-pair-encoding (BPE) as suggested by bpe with selectable number of tokens.

After choosing a tokenization method, a vocabulary will be generated and saved for future inference.

Training methods

The models can be trained using several methods:

Basic Seq2Seq - given encoded sequence, generate (decode) output sequence. Training is done with teacher-forcing.
Multi Seq2Seq - where several tasks (such as multiple languages) are trained simultaneously by using the data sequences as both input to the encoder and output for decoder.
Image2Seq - used to train image to caption generators.

Usage

Example training scripts are available in scripts folder. Inference examples are available in examples folder.

example for training a transformer on WMT16 according to original paper regime:

DATASET=${1:-"WMT16_de_en"}
DATASET_DIR=${2:-"./data/wmt16_de_en"}
OUTPUT_DIR=${3:-"./results"}

WARMUP="4000"
LR0="512**(-0.5)"

python main.py \
  --save transformer \
  --dataset ${DATASET} \
  --dataset-dir ${DATASET_DIR} \
  --results-dir ${OUTPUT_DIR} \
  --model Transformer \
  --model-config "{'num_layers': 6, 'hidden_size': 512, 'num_heads': 8, 'inner_linear': 2048}" \
  --data-config "{'moses_pretok': True, 'tokenization':'bpe', 'num_symbols':32000, 'shared_vocab':True}" \
  --b 128 \
  --max-length 100 \
  --device-ids 0 \
  --label-smoothing 0.1 \
  --trainer Seq2SeqTrainer \
  --optimization-config "[{'step_lambda':
                          \"lambda t: { \
                              'optimizer': 'Adam', \
                              'lr': ${LR0} * min(t ** -0.5, t * ${WARMUP} ** -1.5), \
                              'betas': (0.9, 0.98), 'eps':1e-9}\"
                          }]"

example for training attentional LSTM based model with 3 layers in both encoder and decoder:

python main.py \
  --save de_en_wmt17 \
  --dataset ${DATASET} \
  --dataset-dir ${DATASET_DIR} \
  --results-dir ${OUTPUT_DIR} \
  --model RecurrentAttentionSeq2Seq \
  --model-config "{'hidden_size': 512, 'dropout': 0.2, \
                   'tie_embedding': True, 'transfer_hidden': False, \
                   'encoder': {'num_layers': 3, 'bidirectional': True, 'num_bidirectional': 1, 'context_transform': 512}, \
                   'decoder': {'num_layers': 3, 'concat_attention': True,\
                               'attention': {'mode': 'dot_prod', 'dropout': 0, 'output_transform': True, 'output_nonlinearity': 'relu'}}}" \
  --data-config "{'moses_pretok': True, 'tokenization':'bpe', 'num_symbols':32000, 'shared_vocab':True}" \
  --b 128 \
  --max-length 80 \
  --device-ids 0 \
  --trainer Seq2SeqTrainer \
  --optimization-config "[{'epoch': 0, 'optimizer': 'Adam', 'lr': 1e-3},
                          {'epoch': 6, 'lr': 5e-4},
                          {'epoch': 8, 'lr':1e-4},
                          {'epoch': 10, 'lr': 5e-5},
                          {'epoch': 12, 'lr': 1e-5}]" \

Sequence-to-Sequence learning using PyTorch

Related tags

Overview

Seq2Seq in PyTorch

Installation

Models

Datasets

Training methods

Usage

Owner

Elad Hoffer

Recognition of 38 speech commands in russian. Based on Yandex Cup 2021 ML Challenge: ASR

An assignment from my grad-level data mining course demonstrating some experience with NLP/neural networks/Pytorch

Implementation of COCO-LM, Correcting and Contrasting Text Sequences for Language Model Pretraining, in Pytorch

Index different CKAN entities in Solr, not just datasets

ACL22 paper: Imputing Out-of-Vocabulary Embeddings with LOVE Makes Language Models Robust with Little Cost

A very simple framework for state-of-the-art Natural Language Processing (NLP)

A high-level yet extensible library for fast language model tuning via automatic prompt search

This repository contains the code, data, and models of the paper titled "XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages" published in Findings of the Association for Computational Linguistics: ACL 2021.

Code for Findings at EMNLP 2021 paper: "Learn Continually, Generalize Rapidly: Lifelong Knowledge Accumulation for Few-shot Learning"

Simple program that translates the name of files into English

The guide to tackle with the Text Summarization

OpenAI CLIP text encoders for multiple languages!

RuCLIP tiny (Russian Contrastive Language–Image Pretraining) is a neural network trained to work with different pairs (images, texts).

Mesh TensorFlow: Model Parallelism Made Easier

Test finetuning of XLSR (multilingual wav2vec 2.0) for other speech classification tasks

The entmax mapping and its loss, a family of sparse softmax alternatives.

NAACL 2022: MCSE: Multimodal Contrastive Learning of Sentence Embeddings

Code for CodeT5: a new code-aware pre-trained encoder-decoder model.

Various Algorithms for Short Text Mining

PyKaldi is a Python scripting layer for the Kaldi speech recognition toolkit.