KGSF icon indicating copy to clipboard operation
KGSF copied to clipboard

KDD2020 Improving Conversational Recommender Systems via Knowledge Graph based Semantic Fusion

Results 11 KGSF issues
Sort by recently updated
recently updated
newest added

1、max-r-length和max-c-length表示什么意思呢 2、是不是train_data.jsonl语料中的一些电影没有在id2entity.pkl收录呢,我打断点调试到dataset.py文件里detect_movice()函数中,发现entity = self.id2entity[int(movie)]有时返回为空...

Environment: Pytorch=1.3.0 CUDA=10.1 torch_geometric==1.3.2 Trying to run CUDA_VISIBLE_DEVICES=0 python run.py and getting this error. ![image](https://user-images.githubusercontent.com/23135687/116402237-73d07200-a82c-11eb-91bd-5eacb5aa674e.png) Please suggest a workaround, already spent plenty of time on training but still couldn't achieve...

I have successfully trained both models i.e. recommendation and language. Now I need to generate system responses against seeker queries from the test data set. Please provide any command or...

Hi~ o(* ̄▽ ̄*)ブ,请问论文中,下面这个公式的期望是如何计算的? ![image](https://user-images.githubusercontent.com/11703395/113137327-00503a80-9257-11eb-99d1-67955bec9da5.png) 我在代码里发现了下面的实现,感觉跟论文中描述的方式不太一样?(不知道是不是我看漏了 https://github.com/Lancelot39/KGSF/blob/a10c02cf31dd70d55e972c9ad046df16886f88e1/model.py#L315-L326

Why all the output.txt is null when I load the trained pkl file and use it to val()? Did you cheat in your paper? BTW: To inference , which pkl...

Hi, first of all, thanks for releasing the code and the data. I would like to have a question, how did the file "key2index_3rd.json" come about? Did it come from...

Could you tell me the way you build knowledge graph in the subkg.pkl file? Do you have source code for that?

{'ppl': 0, 'dist1': 0.1659376322844645, 'dist2': 0.4420770424721321, 'dist3': 0.6074502610413433, 'dist4': 0.6902779737547622, 'bleu1': 0.10501320414984876, 'bleu2': 0.029334851364869994, 'bleu3': 0.019595318520804313, 'bleu4': 0.014439181487995948, 'count': 7087} 没有对源码做任何处理,这个是对话模块的实验结果,比论文结果高出了将近20%,有人跑出来也是这样吗?

Hi, I found the total number of DBpedia entities in "/data/entity2entityId.pkl" is 64362. However, in the run.py, the total number of entities is set to be 64368. (also in subkg.pkl),...

Since I'm a new learner, I wonder what the mask4key and mask4movie.npy files stand for. Could anyone tell me what these two files are used for?