“NLP Status Report 2017-8-21”版本间的差异

• done work about code refactoring for poem system

• plan to complete code refactoring for poem system

• organized the results of the experiment
• learned how to use THUMT and how did it work

• train translation models by using THUMT
• test the bleu of these models
• compare with our system

• process data and run model;
• test results.

checkpoint-100000 translation model BLEU： 11.11

• source:在秦者名错，与张仪争论,於是惠王使错将伐蜀，遂拔，因而守之。
• target:在秦国的名叫司马错，曾与张仪发生争论，秦惠王采纳了他的意见，于是司马错率军攻蜀国，攻取后，又让他做了蜀地郡守。
• trans：当时秦国的人都很欣赏他的建议，与张仪一起商议，所以吴王派使者率军攻打蜀地，一举攻，接着又下令守城 。
• source:神大用则竭，形大劳则敝，形神离则死 。
• target:精神过度使用就会衰竭，形体过度劳累就会疲惫，神形分离就会死亡。
• trans: 精神过度就可衰竭,身体过度劳累就会疲惫，地形也就会死。
• source:今天子接千岁之统，封泰山，而余不得从行，是命也夫，命也夫！
• target:现天子继承汉朝千年一统的大业，在泰山举行封禅典礼而我不能随行，这是命啊，是命啊！
• trans: 现在天子可以继承帝位的成就爵位，爵位至泰山，而我却未能执行先帝的命运。

• read source code of seq2seq model;
• 1.data used Zizhitongjian only(6,000 pairs), we can get BLEU 6 at most.
• 2.data used Zizhitongjian only(12,000 pairs), we can get BLEU 7 at most.
• 3.data used Shiji and Zizhitongjian(43,0000 pairs), we can get BLEU about 9.
• 4.data used Shiji and Zizhitongjian(43,0000 pairs), and split the ancient language text one character by one, we can get BLEU 11.11 at most.
• The main factors now is the data(including pairs of sentence、the quality——cause the modern language text include context information.