LeeYuE

same question, i trained the model at the beginging. the scores is : Bleu_1: 0.51006 Bleu_2: 0.36335 Bleu_3: 0.27556 Bleu_4: 0.21658 METEOR: 0.22948 ROUGE_L: 0.52004 is there something wrong? the...

我现在直接使用pipeline测试一下模型的结果，模型直接输出输入的整个context作为答案，好家伙

你好，很想请教一下，你们都是怎么fine tune的呀

Same problem, i tried many times, but the results of BLEU-4 is still between [0.70~0.80]

I also want to know, do you resolve it?

I resolve it, the embedding file "glove.840B.300d.txt" is a word vector word embedding file, you can download here: https://www.kaggle.com/takuok/glove840b300dtxt