PTB数据集和baseline

时间:2022-03-21 04:20:37
【文件属性】:

文件名称:PTB数据集和baseline

文件大小:34.04MB

文件格式:ZIP

更新时间:2022-03-21 04:20:37

NLP

Penn Tree Bank (PTB) dataset, is widely used in machine learning of NLP (Natural Language Processing) research.


【文件预览】:
simple-examples
----models()
--------swb.ngram.model(19.12MB)
--------swb.rnn.model(53.96MB)
--------README(167B)
----2-nbest-rescore()
--------makenbest(6KB)
--------makenbest.c(426B)
--------gettext.c(552B)
--------lattices()
--------getbest(6KB)
--------gettext(6KB)
--------README(3KB)
--------getbest.c(1KB)
----3-combination()
--------train.sh(3KB)
--------test.sh(3KB)
--------README(96B)
----6-recovery-during-training()
--------train.sh(2KB)
--------test.sh(920B)
--------README(335B)
----4-data-generation()
--------train.sh(2KB)
--------test.sh(2KB)
--------README(452B)
----9-char-based-lm()
--------train.sh(2KB)
--------test.sh(957B)
--------README(1KB)
----8-direct()
--------train.sh(3KB)
--------test.sh(2KB)
--------README(1013B)
----rnnlm-0.2b()
--------prob.c(745B)
--------COPYRIGHT.txt(1KB)
--------example.sh(813B)
--------train(330KB)
--------rnnlmlib.h(6KB)
--------convert.c(885B)
--------valid(29KB)
--------rnnlmlib.cpp(49KB)
--------test(34KB)
--------rnnlm.cpp(14KB)
--------example.output(2KB)
--------FAQ.txt(8KB)
--------makefile(411B)
--------CHANGE.log(1KB)
----data()
--------ptb.test.txt(439KB)
--------ptb.char.test.txt(864KB)
--------ptb.train.txt(4.87MB)
--------ptb.char.valid.txt(768KB)
--------ptb.char.train.txt(9.57MB)
--------ptb.valid.txt(390KB)
--------README(609B)
----5-one-iter()
--------train.sh(3KB)
--------test.sh(920B)
--------README(368B)
----1-train()
--------train.sh(2KB)
--------test.sh(1KB)
--------README(211B)
----7-dynamic-evaluation()
--------train.sh(2KB)
--------test.sh(3KB)
--------README(551B)
----temp()

网友评论

  • 请问一下,pdb数据集在哪呢,5积分呢,哎