simple-effective-text-matching-pytorch icon indicating copy to clipboard operation
simple-effective-text-matching-pytorch copied to clipboard

A pytorch implementation of the ACL2019 paper "Simple and Effective Text Matching with Richer Alignment Features".

Results 5 simple-effective-text-matching-pytorch issues
Sort by recently updated
recently updated
newest added

在snli数据集上可以复现实验结果,ACC可以达到89.2 {'acc': 0.8926099348534202, 'loss': 0.3331541208659901, 'score': 0.8926099348534202, 'updates': 136400}

我现在想根据这个模型训练中文,请问需要什么步骤?我应该注意什么吗? 小白求大神们解答

Kindly add pytorch version in the readme as well as pytorch as a dependency in the requirements.txt given the constant evolution of pytorch.

I use quora.json5 to train a new re2, and use the new model to test. But the acc of quora test set can't get 89.2%.

这个代码执行顺序是什么?执行入口在哪里?不报错但是没有结果