Qiming Bao

TypeError: Can't convert 'XXX' to PyBool

1

Hi, I got one issue for this line in the `utils.py` in [this line](https://github.com/nng555/ssmba/blob/master/utils.py#L158). ``` next_len = len(tokenizer.encode(*next_sents)) ``` When I got a list contains three elements, like the following...

Hi, I got 0 accuracy by using the project. How do you get the accuracy result by using the top 20 test question pair? Because those test question pairs are...

Waiting too long for the rouge assessment in Colab

1

 Hi, I just met this issue when I use the file2rouge in colab. The program is running more than 4 hours for the rouge assessment and still without any...

An error when I run the remote connection code

2

 Hi, There is a issue when I run the Model_1.ipynb. It shows the 404 http issue. Does anyone knows how to fix the issue? Many thanks.

Hi, I got one question about the Synonyms and Antonyms function. Can your tool consider the tense when call the Synonyms and Antonyms functions? For example, the synonym for `agrees`...

Hi, I am curious about the inference part in the model. Does any example to show how it works? Many thank.

Hi Akari, I have a question about the augmented transitive example for WIQA. How do you calculate those two phrases are the same for the bold phrases `wood be more...

Transformers和AllenNLP版本问题

5

您好， 感谢更新，很棒的项目！想请问一下您使用的Transformers和AllenNLP的版本是什么？我在本地运行的时候出现版本不兼容的情况，感谢。

关于最终训练结果的展示

1

您好， 感谢您提供这么好的学习资料！我用了ELMO+TextCNN的组合跑了IMDB数据集，得到了下面的结果，想问一下，最后的准确率的计算是应该只算最后一个epoch的accuracy还是把所有epoch的accuracy取平均？另外这个accuracy应该是测试集上的accuracy是吗？因为运行完模型以后没有保存训练的模型，如果能把训练的模型保存下来就更好了。 

请问一下博主知道有ELMO+ESIM的组合开源项目吗？

2

请问一下博主知道有ELMO+ESIM的组合开源项目吗？我搜了目前网上开源的项目，包括提出ELMO+ESIM这个思路的原论文Deep contextualized word representations也没有开源这个组合的代码，我想问一下博主您在这个项目中用到的ELMO+textCNN是不是也是类似ELMO+ESIM的这个架构？多谢了