Tianyi Luo 2016-04-25 - 版本历史

2016年4月25日 (一) 00:36 Lty

2016-04-25T00:36:46Z

2016-04-24T16:20:30Z

2016-04-24T15:56:26Z

2016-04-24T15:56:02Z

2016-04-24T15:42:24Z

2016-04-24T14:36:44Z

2016-04-24T14:35:26Z

2016-04-24T14:12:04Z

2016-04-24T13:36:06Z

2016-04-24T13:22:05Z

@@ 第23行： / 第23行： @@
 * Use entity match rules 4(dpk, ix, lpk sv, dps, s, e, fp, tps, q + machine number + English chacracters) to improve the accuracy from 72.09% to 72.86%.
 * Use entity match rules 5(machine number + English chacracters) to improve the accuracy from 72.86% to 76.48%.
-* Use simlar pair match rules 1(“快”和“速度”、“复写”和“拷贝”等等) to improve the accuracy from 76.48% to ？%.
+* Use simlar pair match rules 1(“快”和“速度”、“复写”和“拷贝”等等) to improve the accuracy from 76.48% to 82.39%.
 === Plan to do next week ===
 * To implement tensorflow version of RNN/LSTM Max margin vector training.

@@ 第16行： / 第16行： @@
 --------------------2016-04-22
 * Speed up process of the test performance about theano version of Generationg the similar questions' vectors based on RNN.
 --------------------2016-04-23
 * Use entity match rule 1(dpk, ix, lpk sv + machine number) to improve the accuracy from 38% to 58%.

@@ 第22行： / 第22行： @@
 * Use entity match rules 4(dpk, ix, lpk sv, dps, s, e, fp, tps, q + machine number + English chacracters) to improve the accuracy from 72.09% to 72.86%.
 * Use entity match rules 5(machine number + English chacracters) to improve the accuracy from 72.86% to 76.48%.
-* Use simlar pair match rules 1(“快”和“速度”、“复写”和“拷贝”等等) to improve the accuracy from 72.86% to 76.48%.
+* Use simlar pair match rules 1(“快”和“速度”、“复写”和“拷贝”等等) to improve the accuracy from 76.48% to ？%.
 === Plan to do next week ===
 * To implement tensorflow version of RNN/LSTM Max margin vector training.

@@ 第22行： / 第22行： @@
 * Use entity match rules 4(dpk, ix, lpk sv, dps, s, e, fp, tps, q + machine number + English chacracters) to improve the accuracy from 72.09% to 72.86%.
 * Use entity match rules 5(machine number + English chacracters) to improve the accuracy from 72.86% to 76.48%.
 === Plan to do next week ===
 * To implement tensorflow version of RNN/LSTM Max margin vector training.

@@ 第21行： / 第21行： @@
 * Use entity match rules 2+3(dps, s, e, fp, tps, q, 200 + machine number and machine number only) to improve the accuracy from 58% to 72.09%.
 * Use entity match rules 4(dpk, ix, lpk sv, dps, s, e, fp, tps, q + machine number + English chacracters) to improve the accuracy from 72.09% to 72.86%.
-* Use entity match rules 5(machine number + English chacracters) to improve the accuracy from 72.86% to ?%.
+* Use entity match rules 5(machine number + English chacracters) to improve the accuracy from 72.86% to 76.48%.
 === Plan to do next week ===
 * To implement tensorflow version of RNN/LSTM Max margin vector training.

@@ 第17行： / 第17行： @@
 * Speed up process of the test performance about theano version of Generationg the similar questions' vectors based on RNN.
 --------------------2016-04-23
-* Use entity match rules to improve the accuracy from 38% to 58%.
+* Use entity match rules(dpk, ix, lpk sv + machine number) to improve the accuracy from 38% to 58%.
 --------------------2016-04-24
-* Use entity match rules to improve the accuracy from 58% to 72%.
+* Use entity match rules(dps, s, e, fp, tps, q, 200 + machine number and machine number only) to improve the accuracy from 58% to 72%.
 === Plan to do next week ===
 * To implement tensorflow version of RNN/LSTM Max margin vector training.

@@ 第12行： / 第12行： @@
 --------------------2016-04-21
 * Finish helping Teacher Wang to prepare for text group's presentation(Tang poetry and Songci generation and Intelligent QA system) for Tsinghua University's 105 anniversary.
-* Submit our IJCAI paper to arxiv. (Solve a big problem about submitting the paper including Chinese chacracters)
+* Submit our IJCAI paper to arxiv. (Solve a big problem about submitting the paper including Chinese chacracters. [http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/How_to_submit_the_latex_files_including_Chinese_characters_to_arxiv Solution])
 * Optimize theano version of Generationg the similar questions' vectors based on RNN.
 --------------------2016-04-22