“RNN test”版本间的差异
来自cslt Wiki
(→RNNLM Rescore) |
(→Test) |
||
第11行: | 第11行: | ||
==Test== | ==Test== | ||
[[wsj_data]] | [[wsj_data]] | ||
+ | [[chinese_data_gigword]] | ||
+ | |||
==chinese data== | ==chinese data== | ||
===prepare data=== | ===prepare data=== |
2014年9月28日 (日) 11:24的版本
tool
- LTSM/RNN training, GPU&deep supported [1]
- RNNLM: RNN LM toolkit [2]
- RWTHLM: RNN LTSM toolkit [3]
- nplm: NN LM, large scale data [4]
- RNN toolkit from microsoft [5]
paper
Steps
Test
chinese data
prepare data
- now data
- gigaword: /work2/xingchao/corpus/Chinese_corpus/gigaword
- bing parallel corpus:/nfs/disk/work/users/xingchao/bing_dict
- baidu:
- sougou:
- using data
- sample gigword about 344M
- dict:tencent11w
- train set
Parameters | hidden | class | direct | bbt | bptt_block | threads | direct-order | rand_seed | nwords | time(min) |
---|---|---|---|---|---|---|---|---|---|---|
set1 | 320 | 300 | 2000 | 2 | 20 | 1 | 4 | 1 | 10000 | 3380(56h) |