NLP Status Report 2016-12-05 - 版本历史

2016年12月5日 (一) 07:53 Zhangjy

2016-12-05T07:53:35Z

2016-12-05T07:42:16Z

2016-12-05T06:50:03Z

2016-12-05T06:48:55Z

2016-12-05T06:06:32Z

2016-12-05T05:57:38Z

2016-12-05T05:47:55Z

2016-12-05T05:45:25Z

2016-12-05T05:43:56Z

2016-12-05T05:38:16Z

@@ 第23行： / 第23行： @@
 *modified memory weight,ran expriment [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/c/c9/Yanqing-weight%282.0%29.pdf 言情风格][http://cslt.riit.tsinghua.edu.cn/mediawiki/images/e/e4/Biansaishi-weight%282.0%29.pdf 边塞风格][http://cslt.riit.tsinghua.edu.cn/mediawiki/images/e/ec/Atten-model.pdf 无风格]
 *read a paper[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/1/1e/1610.09889v1.pdf]
-*simply explain my code to Miss Feng
+*simply explain my code to Professor Feng
 *discussed with liantian about the way of using tensorflow to realize his idea
 ||

@@ 第4行： / 第4行： @@
 | rowspan="5"|2016/12/05
 |Yang Feng ||
-*[[S2S+MN:]] read the code with tensorflow deeply;
+*[[S2S+MN:]] survey another 6 papers (18 papers in total) for data set selection;
 *wrote the mannual for the tensorflow version of s2s [undergoing];
 *[[PoemGen]] discuss the implementation of Jiyuan;

@@ 第9行： / 第9行： @@
 *read Jiyuan's code;
 *[[Huilan's work:]] get the result of integrate syntactic information.
 ||
 *[[rnng+MN:]] do more attempt.

@@ 第4行： / 第4行： @@
 | rowspan="5"|2016/12/05
 |Yang Feng ||
-*[[rnng+MN:]] got the result of k-means method and the result is slightly worse;
+*[[S2S+MN:]] read the code with tensorflow deeply;
-*fixed the bug;
+*wrote the mannual for the tensorflow version of s2s [undergoing];
-*analyzed the memory units and changed the calculation of similarity and reran.
+*[[PoemGen]] discuss the implementation of Jiyuan;
-*[[S2S+MN:]] read the code and discuss with andy about the implementation details;
+*read Jiyuan's code;
-*checked Wikianswers data and found the answers are usually much longer than the question;
+*[[Huilan's work:]] get the result of integrate syntactic information.
-*read 12 QA-related papers in proceedings of ACL16 and EMNLP16 and haven't found proper dataset yet.
-*[[Huilan's work:]] got a version of better result focusing on syntactical transformation.
 ||
-*[[rnng+MN:]] get the result with new similarity calculation.
+*[[rnng+MN:]] do more attempt.
-*[[S2S+MN:]] revise the code of tensorflow to make it equivalent to theano's.
+*[[S2S+MN:]] complete the manual;
-*[[poetry:]] review the code of Jiyuan
+*add MN;
-*[[Huilan's work:]] continue the work of adding syntactic information.
+*[[poetry:]] experiment design；
 |-
 |Jiyuan Zhang ||

@@ 第35行： / 第35行： @@
 |-
 |Shiyue Zhang ||
-* found a bug in my code and modified it.
+* draw tsne pictures  [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/2/2f/RNNG%2Bmm%E5%AE%9E%E9%AA%8C%E6%8A%A5%E5%91%8A.pdf report]]
-* tried memory with gate and found a big problem of memory.
+* try a trained gate to switch between rnng and mem, which got a slightly better result.
-* reran previous models, the results are not better than baseline. [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/2/2f/RNNG%2Bmm%E5%AE%9E%E9%AA%8C%E6%8A%A5%E5%91%8A.pdf report]]
-* reran the original model setting same seed, and got exactly same result.
-* published a TRP [http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/Publication-trp]
 ||
-* try to solve the problem of mem
 |-
 |Guli ||

@@ 第20行： / 第20行： @@
 *restructured code
 *found the cause of cost randomness
-*modified memory weight,ran expriment [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/c/c9/Yanqing-weight%282.0%29.pdf 言情风格][http://cslt.riit.tsinghua.edu.cn/mediawiki/images/e/e4/Biansaishi-weight%282.0%29.pdf 边塞风格]
+*modified memory weight,ran expriment [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/c/c9/Yanqing-weight%282.0%29.pdf 言情风格][http://cslt.riit.tsinghua.edu.cn/mediawiki/images/e/e4/Biansaishi-weight%282.0%29.pdf 边塞风格][http://cslt.riit.tsinghua.edu.cn/mediawiki/images/e/ec/Atten-model.pdf 无风格]
 *read a paper[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/1/1e/1610.09889v1.pdf]
 *simply expain my code to Miss Feng

@@ 第28行： / 第28行： @@
 |-
 |Andi Zhang ||
-*deal with zh2en data set and ran them on NTM
+*turn to focus on tensorflow codes
-*had a small breakthrough about the code
+*finish code outputing encoder outputs but have some problems with format
-−
 ||
-*get output of encoder to form memory
+*finish the part mentioned left
-*continue on the coding work of seq2seq with MemN2N
 |-
 |Shiyue Zhang ||

@@ 第45行： / 第45行： @@
 |-
 |Guli ||
 * preparing more data set
 * working on add translate module to code
+* writing a survey about Chinese-uyghur MT
 ||
 * prepare more data
 * prepare for Thesis Report
 |}