CGMH

CGMH copied to clipboard

This is not a question, just my notes. In sentence correction, CGMH requires an additional `en` package to handle typos or tense errors, which seems not to be distributed by...

kaisugi

When paraphrasing, I am curious about the sample_time and record_time of the config used in the paper. In the code, the model stores record_time every 10 iterations. Does the step(1~5)...

rungjoo

### how to get these sentences? And are they selected by some rulers?

yjs1224

请问一下quora.txt文件的数据格式是什么样的？source和target怎么写

xdge

Any idea on using GPT-2 as the language model for key-gen?

2

Hi Ning, Thanks for your great work and we are wondering if you have any ideas that we can use GPT-2 for keywords-based sentence generation? If that is possible, it...

yuchenlin

How to train the three model

3

when I try to train key_gen model, it may needs 1-billion.txt， but I don't find the txt anywhere. Can you tell me how to train my model and reproduce you...

tiancity-NJU

1-billion.txt

1

请问 1-billion.txt 这个文件在哪下载

J-zin

how to try this model ?

8

I have downloaded the pertained model and try to run in cgmh/ python key_gen.py or cgmh/key_gen/ python key_gen.py. There is a mistake saying that Traceback (most recent call last): File...

tongjinle123

中文数据集做释义生成

3

不好意思哈，为了表达清楚一些，直接上中文了 我在自己的中文数据集上尝试过Guu的Generating sentences by editing prototypes，发现效果挺不错的。后来看了您这篇论文，用您的模型试了下英文上的效果，发现也还挺不错 接下来想跑一下自己的中文数据集对比看看，不知道您之前有在中文上尝试过吗？效果如何？如果我想实现的话需要怎么处理数据呢

Lier007