ConstructingNEEG_IJCAI_2018

ConstructingNEEG_IJCAI_2018 copied to clipboard

利用NEEG与SGNN做预测时，如何从NEEG中海量的事件中找出5个候选事件 When using NEEG and SGNN for prediction, how to find 5 candidate events from the vast number of events in the Graph

1

事件的参数，除了主角，是如何确定的 And how to determine the arguments of those five events , p(a0, a1, a2) , other than the protagonist.

hbhszdh

Interpreting Scores

1

When I try to print out the scores, coming from the 'compute_scores()' function, this is what I get : ```Scores 1 : tensor([[-1.0152, -1.0266, -1.0691, -1.0257, -1.0003], [-0.8766, -0.8788, -0.8806,...

Bharathi-A-7

how to use generate_data.py

3

Thanks for your wonderful code and paper. How to use 'generate_data.py' and embedding methods (e.g., DeepWalk, Skpgram) to build inputs (i.e., files in data such as 'corpus_index_xxxxxxx_with_args_all_chain.data', 'data2.csv', 'test_index.pickle') to...

yangshuodelove

代码中似乎没有找到构建NEEG的代码，想请教是否能实现输入文本，输出基于输入构建的叙事事件图谱？是基于Granroth-Wilding发布的代码去做的么

WxZy530

test_index.pickle文件的作用

2

由于是通过Granroth-wilding的代码重新生成了测试集，需要重新预处理数据。请问test_index.pickle的文件内容是什么？

waltbai

请问这三个文件是怎么得到的

4

data2.csv deepwalk_128_unweighted_with_args.txt encoding_with_args.csv 您好，请问这三个文件是怎么得到的

ReadyTeresa

raw NYT news corpus

1

请问大家原始数据在哪里下载呢，作者给的链接里好像没有找到

KyrieIrving24

input data format

1

could you elaborate the format of corpus_index_*.txt, I load it with pickle and see a struture of lists, [ "gives", "give", "obj", "surplus", "city", null ], what are the meanings...

MikeWangWZHL

RuntimeError: CUDA out of memory.

1

When I run the event_chain.py, I encountered the run time error problem "RuntimeError: CUDA out of memory. Tried to allocate 474.75 MiB (GPU 0; 5.93 GiB total capacity; 4.39 GiB...

jianzhengming

Train my own data

1

We note that the data you provide is already processed data. If I want to train my own data, what do I need to do

li-2132