ammieqi / synpg Goto Github PK

@inproceedings{Huang2021synpg,
    author    = {Kuan-Hao Huang and
                 Kai-Wei Chang},
    title     = {Generating Syntactically Controlled Paraphrases without Using Annotated Parallel Pairs},
    booktitle = {Proceedings of the Conference of the European Chapter of the Association for Computational Linguistics (EACL)},
    year      = {2021},
}

$ pip install -r requirements.txt

python generate.py \
    --synpg_model_path ./model/pretrained_synpg.pt \
    --pg_model_path ./model/pretrained_parse_generator.pt \
    --input_path ./demo/input.txt \
    --output_path ./demo/output.txt \
    --bpe_codes_path ./data/bpe.codes \
    --bpe_vocab_path ./data/vocab.txt \
    --bpe_vocab_thresh 50 \
    --dictionary_path ./data/dictionary.pkl \
    --max_sent_len 40 \
    --max_tmpl_len 100 \
    --max_synt_len 160 \
    --temp 0.5 \
    --seed 0

python train_synpg.py \
    --model_dir ./model \
    --output_dir ./output \
    --bpe_codes_path ./data/bpe.codes \
    --bpe_vocab_path ./data/vocab.txt \
    --bpe_vocab_thresh 50 \
    --dictionary_path ./data/dictionary.pkl \
    --train_data_path ./data/train_data.h5 \
    --valid_data_path ./data/valid_data.h5 \
    --emb_path ./data/glove.840B.300d.txt \
    --max_sent_len 40 \
    --max_synt_len 160 \
    --word_dropout 0.4 \
    --n_epoch 5 \
    --batch_size 64 \
    --lr 1e-4 \
    --weight_decay 1e-5 \
    --log_interval 250 \
    --gen_interval 5000 \
    --save_interval 10000 \
    --temp 0.5 \
    --seed 0

python train_parse_generator.py \
    --model_dir ./model \
    --output_dir ./output_pg \
    --dictionary_path ./data/dictionary.pkl \
    --train_data_path ./data/train_data.h5 \
    --valid_data_path ./data/valid_data.h5 \
    --max_sent_len 40 \
    --max_tmpl_len 100 \
    --max_synt_len 160 \
    --word_dropout 0.2 \
    --n_epoch 5 \
    --batch_size 32 \
    --lr 1e-4 \
    --weight_decay 1e-5 \
    --log_interval 250 \
    --gen_interval 5000 \
    --save_interval 10000 \
    --temp 0.5 \
    --seed 0