wassname/Castor
1
0
Fork 0
mirror of https://github.com/wassname/Castor.git synced 2026-09-09 11:13:20 +08:00
Code Issues Packages Projects Releases Wiki Activity

MP-CNN: Add hyperparameters used to achieve paper perf for WikiQA (#82)

Browse Source
This commit is contained in:
Michael Tu
2017-11-08 09:51:04 -05:00
committed by GitHub
parent aaff291edb
commit 0722dde06e
1 changed files with 16 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
mp_cnn/README.md
+16
View File
@@ -61,6 +61,22 @@ python main.py mpcnn.trecqa.model --dataset trecqa --epochs 5 --regularization 0
The paper results are reported in [Noise-Contrastive Estimation for Answer Selection with Deep Neural Networks](https://dl.acm.org/citation.cfm?id=2983872).
## WikiQA Dataset
You also need `trec_eval` for this dataset, similar to TrecQA.
Then, you can run:
```
python main.py mpcnn.wikiqa.model --epochs 10 --dataset wikiqa --batch-size 64 --lr 0.0004 --regularization 0.02
```
| Implementation and config | map | mrr |
| -------------------------------- |:------:|:------:|
| Paper | 0.693 | 0.709 |
| PyTorch using above config | 0.693 | 0.7091 |
The paper results are reported in [Noise-Contrastive Estimation for Answer Selection with Deep Neural Networks](https://dl.acm.org/citation.cfm?id=2983872).
These are not the optimal hyperparameters but they are decent. This README will be updated with more optimal hyperparameters and results in the future.
To see all options available, use