“NLP Status Report 2017-6-5”版本间的差异
来自cslt Wiki
| 第2行： | 第2行： | ||
!Date !! People !! Last Week !! This Week | !Date !! People !! Last Week !! This Week | ||
|- | |- | ||
| − | | rowspan="6"|2017/ | + | | rowspan="6"|2017/6/5 |
|Jiyuan Zhang || | |Jiyuan Zhang || | ||
|| | || | ||
| 第13行： | 第13行： | ||
* big data baseline bleu = '''30.83''' | * big data baseline bleu = '''30.83''' | ||
* Fixed three embeddings | * Fixed three embeddings | ||
| − | + | Shrink output vocab from 30000 to 20000 and best result is 31.53 | |
| − | + | Train the model with 40 batch size and best result until now is 30.63 | |
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
|} | |} | ||
| − | * | + | * test more checkpoints on model trained with batch = 40 |
| − | + | * train model with reverse output | |
|| | || | ||
2017年6月5日 (一) 05:44的版本
| Date | People | Last Week | This Week |
|---|---|---|---|
| 2017/6/5 | Jiyuan Zhang | ||
| Aodong LI |
Only make the English encoder's embedding constant -- 45.98 Only initialize the English encoder's embedding and then finetune it -- 46.06 Share the attention mechanism and then directly add them -- 46.20
Shrink output vocab from 30000 to 20000 and best result is 31.53 Train the model with 40 batch size and best result until now is 30.63 |
- test more checkpoints on model trained with batch = 40
- train model with reverse output
||
|- |Shiyue Zhang ||
||
|- |Shipan Ren ||
||
|-
|}
