RNN test

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]

Steps

process dict and data

Test

wsj_data

chinese_data_gigword

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

Train Set Environment

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)