Fan

When I tried to reproduce this paper, I found that six files were read in the source code, namely tr.pkl vl.pkl ts.pkl and pre_tr.pkl pre_vl.pkl pre_ts.pkl. I know the format...

一些代码运行问题（batch_size>1；bert的使用以及opinion_offset的设置）

2

您好，在运行您的项目时我有以下几个问题想要请教： 1. 在您的项目中对于batch_size>1的相关处理代码还是抽象方法： 比如triplet/hypergraph/NeuralBuilder.py 中的 def generate_batches(self, train_insts, batch_size)和def build_nn_graph_batch(self, batch_input_seqs)； 请问这部分您后来有更新吗？ 2. 不使用bert，您的代码可以正常运行；但是使用bert会出现out-of-memory的问题，不知道您是否有什么优化方法？ 3. 当我尝试复现opinion_offset=7（即论文中的M=6）的结果时，运行速度有些过慢：以res15为例： ``` Start Training... toal num of entity: 249 total num of prediction: 157 Dev...

I don't understand why the reasoning effect of reloading the trained model is very poor. Did I write something wrong? Looking forward to your reply. the key code is as...

14res结果无法复现

2

您好，在对您论文得到的结果进行复现时，对于extraction-style上14res的结果（我设置了多个随机种子进行运行），均与您论文结果相差较大 

Could you kindly share your thesis?

1

I am very interested about your project. Where can I download your thesis?