Files
2016-08-15 12:38:21 -07:00

42 lines
805 B
Plaintext

Best results achieved for each model:
Embedding + Max Pooling:
- Top 1 Precision:
- 0.492 on test 1
- 0.483 on test 2
- 0.495 on dev
- MRR:
- 0.624 on test 1
- 0.611 on test 2
- 0.624 on dev
Attentional LSTM + Max Pooling:
- Top 1 precision:
- 0.480 on test 1
- 0.465 on test 2
- 0.487 on dev
- MRR:
- 0.627 on test 1
- 0.613 on test 2
- 0.635 on dev
Unsupervised RNN language model + trained embeddings:
- Top 1 precision:
- 0.546 on test 1
- 0.527 on test 2
- 0.552 on dev
- MRR:
- 0.670 on test 1
- 0.651 on test 2
- 0.671 on dev
Training ConvolutionalLSTM model for a long time (~4 days):
- Top-1 Precision:
- 0.564 on test 1
- 0.543 on test 2
- 0.573 on dev
- MRR:
- 0.681 on test 1
- 0.661 on test 2
- 0.686 on dev