New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Reproducing NELL-995 MAP Results #1
Comments
Hi Victoria, |
Hi Shehzaad, I generated the results by running scripts in the repo, so yes, I think the grapher should be the same as yours. It uses the graph named "graph.txt" in the I did the evaluation by extracting the prediction scores of MINERVA written in the |
@shehzaadzd Any updates on this one? |
Hi Victoria, |
Thanks very much. I will check the difference and get back to you. |
@shehzaadzd @todpole3, I encounter the same problem. What is the test_prediction_path data format? I think there seems to be a script to parse the results in test_beam? |
Hi Po sen, I've uploaded the answers generated by our model on each nell task. (link). I'm adding the code to print these answers in our main repo and I will push it soon. Hope this helps. |
Thanks a lot! Looking forward to the script. @shehzaadzd, any update for the script? |
@posenhuang - We apologize for the late reply from our side. To train on one relation; you can train on the individual graphs (exactly as in the DeepPath). For example, the data for concept:worksfor would be in here. |
Thanks, I haven't been experimenting with this dataset lately. Will check and let you know. |
Thanks very much for the nice code! I reproduce the experiment on the dataset NELL, However, when i generate separate models on each nell tasks using the default config files.(using_entity_embedding=1 for all task) I can produce almost all result of task. the config file i used is below:
Even the answer you provided seems correct, I still want to make sure I did set the hyperparameters to the correct value for your single model for all the relations?? Thanks a lot!!! |
Hi Lee, |
Thanks for telling me this, I will run the model on nell-995 dataset and check the result ! ! |
Hi shehzaadzd
config file:
I also try to set the embedding size and hidden size to 50 ,the result is below
config file:
finally , i set the LSTM Layers to 3 according to your paper, the result
However, none of the results are similar to the result in paper, I think i set the hyperparameters completely according to the paper or the appendix. is my config file the optimal parameter for your experiment. Could you help me to reproduce the results? Thanks a lot !!!!!!!! |
Thanks very much for releasing the code in accompany with the paper. It definitely makes reproducing the experiments a lot easier. I've been playing with the code base and have some questions on reproducing the NELL-995 experiments.
The codebase does not contain the configuration file for NELL-995 experiments, nor does it contains the evaluation scripts for computing MAP. (Maybe you've missed them from the release?)
I used the hyperparameters reported in "Experimental Details, section 2.3" and the appendix section 8.1 of the paper, which results in the following configuration file:
I run train & test as specified in the README, and evaluate the decoding results using the MAP computation script produced by the DeepPath paper. (I assumed that the experiment setup is exactly the same as the DeepPath paper since you compared head-to-head with them.)
However, the MAP results I obtained this way is significantly lower compared to the reported results.
I did a few variation on embedding dimensions and also tried to freeze entity embeddings, yet none of the trials produced numbers close to the results tabulated in the MINERVA paper.
Would you please clarify the experiment setup for computing MAP?
I want to make sure I did set the hyperparameters to the correct value. Besides, the DeepPath paper used a relation-dependent underlying graph per relation during inference. Did you also vary the graph per relation or used a base graph for all relations like you did for other datasets?
Many thanks.
The text was updated successfully, but these errors were encountered: