FSMT

模型描述

这是fairseq基于 wmt19 transformer 进行的de-en的移植版本。

更多详情请参考 Deep Encoder, Shallow Decoder: Reevaluating the Speed-Quality Tradeoff in Machine Translation 。

提供两个模型：

• wmt19-de-en-6-6-big
• wmt19-de-en-6-6-base

使用方法和限制

from transformers import FSMTForConditionalGeneration, FSMTTokenizer
mname = "allenai/wmt19-de-en-6-6-big"
tokenizer = FSMTTokenizer.from_pretrained(mname)
model = FSMTForConditionalGeneration.from_pretrained(mname)

input = "Maschinelles Lernen ist großartig, nicht wahr?"
input_ids = tokenizer.encode(input, return_tensors="pt")
outputs = model.generate(input_ids)
decoded = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(decoded) # Machine learning is great, isn't it?

训练数据

预训练权重与allenai发布的原始模型保持一致。更多详情请参考 paper 。

评估结果

这里是BLEU分数：

分数是使用以下代码计算的：

git clone https://github.com/huggingface/transformers
cd transformers
export PAIR=de-en
export DATA_DIR=data/$PAIR
export SAVE_DIR=data/$PAIR
export BS=8
export NUM_BEAMS=5
mkdir -p $DATA_DIR
sacrebleu -t wmt19 -l $PAIR --echo src > $DATA_DIR/val.source
sacrebleu -t wmt19 -l $PAIR --echo ref > $DATA_DIR/val.target
echo $PAIR
PYTHONPATH="src:examples/seq2seq" python examples/seq2seq/run_eval.py allenai/wmt19-de-en-6-6-big $DATA_DIR/val.source $SAVE_DIR/test_translations.txt --reference_path $DATA_DIR/val.target --score_path $SAVE_DIR/test_bleu.json --bs $BS --task translation --num_beams $NUM_BEAMS

数据来源

• training, etc.
• test set

BibTeX条目和引用信息

@misc{kasai2020deep,
    title={Deep Encoder, Shallow Decoder: Reevaluating the Speed-Quality Tradeoff in Machine Translation},
    author={Jungo Kasai and Nikolaos Pappas and Hao Peng and James Cross and Noah A. Smith},
    year={2020},
    eprint={2006.10369},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}