Non-Monotonic Sequential Text Generation

PyTorch implementation of the paper:

Non-Monotonic Sequential Text Generation
Sean Welleck, Kiante Brantley, Hal Daume III, Kyunghyun Cho
ICML 2019

We present code and data for training models described in the paper, and notebooks for evaluating pre-trained models.

Installation

python setup.py develop

Data

For downloading the datasets below, it may be helpful to use gdown.pl.

Persona Chat (Unconditional Generation, Word-Reordering)

Google drive
Put the .jsonl files into a directory {PCHAT_DIR}.

Machine Translation

Google drive
Unzip the dataset, e.g. to /path/to/iwslt. Then {MT_DIR} below will be /path/to/iwslt/IWSLT/en-de/.

Using a Pretrained Model

You can use and evaluate pre-trained models in one of the provided notebooks:

Task	Models	Notebook
Word Reordering	Google drive	notebooks/word_reorder_eval.ipynb
Unconditional Generation	Google drive	notebooks/unconditional_eval.ipynb
Translation (Transformer)	Google drive	notebooks/translation_eval.ipynb

The word-reordering and translation notebooks reproduce the evaluation metrics (e.g. BLEU) in the paper.

The unconditional notebook demos the models via interactive sampling and tree completion.

Training

First download and unzip GloVe vectors into a directory {GLOVE_DIR}.

Word-Reordering

python tree_text_gen/binary/bagorder/train.py --glovepath {GLOVE_DIR}/glove.840B.300d.txt \
                                              --datadir {PCHAT_DIR}

Unconditional Generation

python tree_text_gen/binary/unconditional/train.py --glovepath {GLOVE_DIR}/glove.840B.300d.txt \
                                                   --datadir {PCHAT_DIR}

Machine Translation (Transformer)

python tree_text_gen/binary/translation/train_transformer.py --datadir {MT_DIR}

Use --multigpu for multi-GPU.

Machine Translation (LSTM)

python tree_text_gen/binary/translation/train.py --datadir {MT_DIR} --model-type translation \
                                                 --beta-burnin 2 --beta-step 0.05 \
                                                 --self-teach-beta-step 0.05

By default these commands train policies with the annealed oracle. See tree_text_gen/{bagorder, unconditional, translation}/args.py for hyper-parameters and arguments.

wellecks / nonmonotonic_text