“Schedule”版本间的差异

来自cslt Wiki
跳转至： 导航、 搜索
（→‎Daily Report）
（→‎Daily Report）
 
（10位用户的226个中间修订版本未显示）
第9行： 第9行：
 
* Aodong Li (李傲冬)
 
* Aodong Li (李傲冬)
 
* Andi Zhang (张安迪)
 
* Andi Zhang (张安迪)
−
* Ziwei Bai （白子薇）
 
−
* Aiting Liu (刘艾婷)
 
−
* Shiyao Li （李诗瑶）
 
 
* Shiyue Zhang (张诗悦)
 
* Shiyue Zhang (张诗悦)
 +
* Li Gu (古丽)
 +
* Peilun Xiao (肖培伦)
 +
* Shipan Ren (任师攀)
 +
* Jiayu Guo (郭佳雨)
  
 
===Former Members===
 
===Former Members===
第23行： 第24行：
 
* '''DongXu Zhang (张东旭)''': --
 
* '''DongXu Zhang (张东旭)''': --
 
* '''Yiqiao Pan (潘一桥)'''  ： MA candidate in University of Sydney  
 
* '''Yiqiao Pan (潘一桥)'''  ： MA candidate in University of Sydney  
−
 
+
* '''Shiyao Li （李诗瑶）''' :  BUPT
 +
* '''Aiting Liu (刘艾婷)'''  :  BUPT
  
 
==Work Progress==
 
==Work Progress==
第31行： 第33行：
 
! Date !! Person  !! start!! leave !! hours ||status
 
! Date !! Person  !! start!! leave !! hours ||status
 
|-
 
|-
−
| rowspan="5"|2016/10/01
+
| rowspan="2"|2017/04/02
−
|Ziwei Bai || ||   || ||
+
|Andy Zhang||9:30 ||18:30 ||8 ||  
 +
*preparing EMNLP
 
|-
 
|-
−
|Andy Zhang|| || ||||  
+
|Peilun Xiao || || || ||
 
|-
 
|-
−
|Shiyue Zhang || 9:30|| 20:30|| 9 ||  
+
| rowspan="2"|2017/04/03
−
*write the use guide of RNNG
+
|Andy Zhang||9:30 ||18:30 ||8 ||  
 +
*preparing EMNLP
 
|-
 
|-
−
|Aodong Li || ||   || ||
+
|Peilun Xiao || || || ||
 
|-
 
|-
−
|Shiyao Li || || || ||  
+
| rowspan="2"|2017/04/04
 +
|Andy Zhang||9:30 ||18:30 ||8 ||
 +
*preparing EMNLP
 
|-
 
|-
−
| rowspan="5"|2016/10/08
+
|Peilun Xiao || || || ||
−
|Ziwei Bai || 10:00 || 22:00  || 11 ||
+
−
*Thesaurus data crawling
+
 
|-
 
|-
−
|Andy Zhang||9:40 ||19:30 ||8+  || reviewed source code of Menn2n
+
| rowspan="2"|2017/04/05
 +
|Andy Zhang||9:30 ||18:30 ||8 ||  
 +
*preparing EMNLP
 
|-
 
|-
−
|Shiyue Zhang || 9:30 || 20:30 || 10 ||  
+
|Peilun Xiao || || || ||
−
* write the RNNG use guide
+
 
|-
 
|-
−
|Aodong Li || ||   || ||
+
| rowspan="2"|2017/04/06
 +
|Andy Zhang||9:30 ||18:30 ||8 ||
 +
*preparing EMNLP
 
|-
 
|-
−
|Shiyao Li || || || ||  
+
|Peilun Xiao || || || ||
 
|-
 
|-
−
| rowspan="5"|2016/10/09
+
| rowspan="2"|2017/04/07
−
|Ziwei Bai || 10:30 || 23:00  || 12 ||
+
|Andy Zhang||9:30 ||18:30 ||8 ||  
−
*build process of Chinese characters phonetic
+
*preparing EMNLP
 
|-
 
|-
−
|Andy Zhang||9:30 ||19:30 ||9  || reviewed source code of Menn2n
+
|Peilun Xiao || || || ||
 
|-
 
|-
−
|Shiyue Zhang || 9:30 || 18: 30|| 8 ||  
+
| rowspan="2"|2017/04/08
−
* finish the RNNG use guide
+
|Andy Zhang||9:30 ||18:30 ||8 ||  
−
* try new way to run RNNG with the updated RNNG code repos
+
*preparing EMNLP
 
|-
 
|-
−
|Aodong Li || ||   || ||
+
|Peilun Xiao || || || ||
 
|-
 
|-
−
|Shiyao Li || || || ||  
+
| rowspan="2"|2017/04/09
 +
|Andy Zhang||9:30 ||18:30 ||8 ||
 +
*preparing EMNLP
 
|-
 
|-
−
| rowspan="5"|2016/10/10
+
|Peilun Xiao || || || ||
−
|Ziwei Bai || 10:00 || 21:00  || 10 ||
+
−
*seek and buy some data from internet
+
 
|-
 
|-
−
|Andy Zhang||9:30 ||19:30 ||9  || prepared for paper sharing
+
| rowspan="2"|2017/04/10
 +
|Andy Zhang||9:30 ||18:30 ||8 ||  
 +
*preparing EMNLP
 
|-
 
|-
−
|Shiyue Zhang || 13:40 || 19:00|| 5 ||
+
|Peilun Xiao || || || ||
−
* try new way to run RNNG on my own computer
+
 
|-
 
|-
−
|Aodong Li || ||   || ||
+
| rowspan="2"|2017/04/11
 +
|Andy Zhang||9:30 ||18:30 ||8 ||
 +
*preparing EMNLP
 
|-
 
|-
−
|Shiyao Li || || || ||  
+
|Peilun Xiao || || || ||
 
|-
 
|-
−
| rowspan="5"|2016/10/11
+
| rowspan="2"|2017/04/12
−
|Ziwei Bai || 10:00 || 21:00  || 10 ||  
+
|Andy Zhang||9:30 ||18:30 ||8 ||  
−
*crawl data
+
*preparing EMNLP
 
|-
 
|-
−
|Andy Zhang||9:30 ||19:30 ||9  || prepared for paper sharing about a QA model
+
|Peilun Xiao || || || ||
 
|-
 
|-
−
|Shiyue Zhang || 9:30 || 18:30 || 8 ||
+
| rowspan="2"|2017/04/13
−
* reviewed the RNNG code 
+
|Andy Zhang||9:30 ||18:30 ||8 ||  
−
* read the paper "Multi-Way, Multilingual Neural Machine Translation with a Shared Attention Mechanism"
+
*preparing EMNLP
 
|-
 
|-
−
|Aodong Li || ||   || ||
+
|Peilun Xiao || || || ||
 
|-
 
|-
−
|Shiyao Li || || || ||  
+
| rowspan="2"|2017/04/14
 +
|Andy Zhang||9:30 ||18:30 ||8 ||
 +
*preparing EMNLP
 
|-
 
|-
−
| rowspan="5"|2016/10/12
+
|Peilun Xiao || || || ||
−
|Ziwei Bai || 10:00 || 21:00  || 10 ||
+
−
*crawl data
+
 
|-
 
|-
−
|Andy Zhang||9:30 ||19:30 ||9  ||  
+
| rowspan="2"|2017/04/15
−
*discuss source code of Memn2n with Mrs. Feng
+
|Andy Zhang||9:00 ||15:00 ||6 ||  
−
*reviewed the preparation
+
*preparing EMNLP
 
|-
 
|-
−
|Shiyue Zhang || 14:30  || 20:30 || 5 ||  
+
|Peilun Xiao || || || ||
−
* discuss the code of RNNG with Teacher Feng
+
 
|-
 
|-
−
|Aodong Li || ||   || ||
+
| rowspan="1"|2017/04/18
 +
|Aodong Li||11:00 ||20:00 ||8 ||  
 +
*Pick up new task in news generation and do literature review
 
|-
 
|-
−
|Shiyao Li || || || ||  
+
| rowspan="1"|2017/04/19
 +
|Aodong Li||11:00 ||20:00 ||8 ||  
 +
*Literature review
 
|-
 
|-
−
| rowspan="5"|2016/10/13
+
| rowspan="1"|2017/04/20
−
|Ziwei Bai || 10:00 || 21:00 || 10 ||
+
|Aodong Li||12:00 ||20:00 ||8 ||  
−
*crawl data
+
*Literature review
 
|-
 
|-
−
|Andy Zhang||9:30 ||19:30 ||9  || solved some problems met in the paper with Mrs. Feng
+
| rowspan="1"|2017/04/21
 +
|Aodong Li||12:00 ||20:00 ||8 ||  
 +
*Literature review
 
|-
 
|-
−
|Shiyue Zhang || || || ||  
+
| rowspan="1"|2017/04/24
 +
|Aodong Li||11:00 ||20:00 ||8 ||
 +
*Adjust literature review focus
 
|-
 
|-
−
|Aodong Li || ||   || ||
+
| rowspan="1"|2017/04/25
 +
|Aodong Li||11:00 ||20:00 ||8 ||  
 +
*Literature review
 
|-
 
|-
−
|Shiyao Li || || || ||  
+
| rowspan="1"|2017/04/26
 +
|Aodong Li||11:00 ||20:00 ||8 ||  
 +
*Literature review
 
|-
 
|-
−
| rowspan="5"|2016/10/14
+
| rowspan="1"|2017/04/27
−
|Ziwei Bai || 10:00 || 21:00 || 10 ||  
+
|Aodong Li||11:00 ||20:00 ||8 ||  
−
*crawl data
+
*Try to reproduce sc-lstm work
 
|-
 
|-
−
|Andy Zhang||9:30 ||18:30 ||8 ||  
+
| rowspan="1"|2017/04/28
−
*shared the paper
+
|Aodong Li||11:00 ||20:00 ||8 ||  
−
*should start to read about attention mechanism
+
*Transfer to new task in machine translation and do literature review
 
|-
 
|-
−
|Shiyue Zhang || 9:30 || 18:30 || 8 ||
+
| rowspan="1"|2017/04/30
−
* simplify RNNG use guide with the new way to run it
+
|Aodong Li||11:00 ||20:00 ||8 ||  
−
* share the paper
+
*Literature review
 
|-
 
|-
−
|Aodong Li || ||   || ||
+
| rowspan="1"|2017/05/01
 +
|Aodong Li||11:00 ||20:00 ||8 ||  
 +
*Literature review
 
|-
 
|-
−
|Shiyao Li || || || ||  
+
| rowspan="1"|2017/05/02
 +
|Aodong Li||11:00 ||20:00 ||8 ||  
 +
*Literature review and code review
 
|-
 
|-
−
| rowspan="5"|2016/10/15
+
| rowspan="1"|2017/05/06
−
|Ziwei Bai || 12:00 || 22:00  || 9 ||  
+
|Aodong Li||14:20 ||17:20||3 ||  
−
*crawl data
+
*Code review
 
|-
 
|-
−
|Andy Zhang|| || || ||  
+
| rowspan="1"|2017/05/07
 +
|Aodong Li||13:30 ||22:00||8 ||
 +
*Code review and experiment started, but version discrepancy encountered
 
|-
 
|-
−
|Shiyue Zhang || || || ||
+
| rowspan="1"|2017/05/08
 +
|Aodong Li||11:30 ||21:00 ||8 ||
 +
*Code review and version discrepancy solved
 
|-
 
|-
−
|Aodong Li || ||   || ||
+
| rowspan="1"|2017/05/09
 +
|Aodong Li||13:00 ||22:00 ||9 ||  
 +
*Code review and experiment
 +
*details about experiment:
 +
  small data,
 +
  1st and 2nd translator uses the same training data,
 +
  2nd translator uses '''random initialized embedding'''
 +
*results (BLEU):
 +
  BASELINE: 43.87
 +
  best result of our model: 42.56
 
|-
 
|-
−
|Shiyao Li || || || ||  
+
| rowspan="1"|2017/05/10
 +
|Shipan Ren || 9:00 || 20:00 || 11 ||
 +
*Entry procedures
 +
*Machine Translation paper reading
 
|-
 
|-
−
| rowspan="5"|2016/10/16
+
| rowspan="1"|2017/05/10
−
|Ziwei Bai || 14:00 || 22:00 || 7.5 ||
+
|Aodong Li || 13:30 || 22:00 || 8 ||  
−
* deal with the text data
+
*experiment setting:
 +
  small data,
 +
  1st and 2nd translator uses the different training data, counting 22000 and 22017 seperately
 +
  2nd translator uses '''random initialized embedding'''
 +
*results (BLEU):
 +
  BASELINE: 36.67 (36.67 is the model at 4750 updates, but we use model at 3000 updates to
 +
                    prevent the case of overfitting, to generate the 2nd translator's training data, for
 +
                    which the BLEU is 34.96)
 +
  best result of our model: 29.81
 +
  This may suggest that that using either the same training data with 1st translator or different
 +
                    one won't influence 2nd translator's performance, instead, using the same one may
 +
                    be better, at least from results. But I have to give a consideration of a smaller size
 +
                    of training data compared to yesterday's model.
 +
*code 2nd translator with constant embedding
 
|-
 
|-
−
|Andy Zhang|| || || ||  
+
| rowspan="1"|2017/05/11
 +
|Shipan Ren || 10:00 || 19:30 || 9.5 ||
 +
*Configure environment
 +
*Run tf_translate code
 +
*Read Machine Translation paper
 
|-
 
|-
−
|Shiyue Zhang || || || ||  
+
| rowspan="1"|2017/05/11
 +
|Aodong Li || 13:00 || 21:00|| 8 ||
 +
*experiment setting:
 +
  small data,
 +
  1st and 2nd translator uses the same training data,
 +
  2nd translator uses '''constant untrainable embedding''' imported from 1st translator's decoder
 +
*results (BLEU):
 +
  BASELINE: 43.87
 +
  best result of our model: 43.48
 +
  Experiments show that this kind of series or cascade model will definitely impair the final perfor-
 +
                      mance due to information loss as the information flows through the network from
 +
                      end to end. Decoder's smaller vocabulary size compared to encoder's demonstrate
 +
                      this (9000+ -> 6000+).
 +
  The intention of this experiment is looking for a map to solve meaning shift using 2nd translator,
 +
                      but result of whether the map is learned or not is obscured by the smaller vocab size
 +
                      phenomenon.
 +
*literature review on hierarchical machine translation
 
|-
 
|-
−
|Aodong Li || ||   || ||
+
| rowspan="1"|2017/05/12
 +
|Aodong Li||13:00 ||21:00 ||8 ||  
 +
*Code double decoding model and read multilingual MT paper
 
|-
 
|-
−
|Shiyao Li || || || ||  
+
| rowspan="1"|2017/05/13
 +
|Shipan Ren || 10:00 || 19:00 || 9 ||
 +
*read machine translation paper
 +
*learne lstm model and seq2seq model
 
|-
 
|-
−
| rowspan="5"|2016/10/17
+
| rowspan="1"|2017/05/14
−
|Ziwei Bai || 13:00 || 22:00   || 8 ||
+
|Aodong Li || 10:00 || 20:00 || 9 ||  
 +
*Code double decoding model and experiment
 +
*details about experiment:
 +
  small data,
 +
  2nd translator uses as training data the concat(Chinese, machine translated English),
 +
  2nd translator uses '''random initialized embedding'''
 +
*results (BLEU):
 +
  BASELINE: 43.87
 +
  best result of our model: 43.53
 +
*NEXT: 2nd translator uses '''trained constant embedding'''
 
|-
 
|-
−
|Andy Zhang|| 9:30||19:00 ||8+ || read source code of seq2seq
+
| rowspan="1"|2017/05/15
 +
|Shipan Ren || 9:30 || 19:00 || 9.5 ||  
 +
* understand the difference between lstm model and gru model
 +
* read the implement code of seq2seq model
 
|-
 
|-
−
|Shiyue Zhang || 14:20 || 20:40 || 6 ||  
+
| rowspan="2"|2017/05/17
−
* read the paper "End to end Memory Networks
+
|Shipan Ren || 9:30 || 19:30 || 10 ||  
−
* try to run MemNN-lang code  
+
* read neural machine translation paper
 +
* read tf_translate code
 
|-
 
|-
−
|Aodong Li || ||   || ||
+
|Aodong Li || 13:30 || 24:00 || 9||  
 +
* code and debug double-decoder model
 +
* alter 2017/05/14 model's size and will try after nips
 
|-
 
|-
−
|Shiyao Li || || || ||  
+
| rowspan="2"|2017/05/18
 +
|Shipan Ren || 10:00 || 19:00 || 9 ||
 +
* read neural machine translation paper
 +
* read tf_translate code
 
|-
 
|-
−
| rowspan="5"|2016/10/18
+
|Aodong Li || 12:30 || 21:00 || 8 ||  
−
|Ziwei Bai || 9:30 || 21:30  || 11  ||
+
* train double-decoder model on small data set but encounter decode bugs
 
|-
 
|-
−
|Andy Zhang||10:00 || 19:30||8+ || read source code of seq2seq
+
| rowspan="1"|2017/05/19
 +
|Aodong Li || 12:30 || 20:30 || 8 ||  
 +
* debug double-decoder model
 +
* the model performs well on develop set, but performs badly on test data. I want to figure out the reason.
 
|-
 
|-
−
|Shiyue Zhang || 9:20 || 20:00 || 9+ ||
+
| rowspan="1"|2017/05/21
−
* run MemNN code successfully
+
|Aodong Li || 10:30 || 18:30 || 8 ||  
−
* read the code and try to understand
+
*details about experiment:
 +
  hidden_size = 700 (500 in prior)
 +
  emb_size = 510 (310 in prior)
 +
  small data,
 +
  2nd translator uses as training data the concat(Chinese, machine translated English),
 +
  2nd translator uses '''random initialized embedding'''
 +
*results (BLEU):
 +
  BASELINE: 43.87
 +
  best result of our model: '''45.21'''
 +
  But only one checkpoint outperforms the baseline, the other results are commonly under 43.1
 +
* debug double-decoder model
 
|-
 
|-
−
|Aodong Li || ||   || ||
+
| rowspan="1"|2017/05/22
 +
|Aodong Li || 14:00 || 22:00 || 8 ||  
 +
*double-decoder without joint loss generalizes very bad
 +
*i'm trying double-decoder model with joint loss
 
|-
 
|-
−
|Shiyao Li || || || ||  
+
| rowspan="1"|2017/05/23
 +
|Aodong Li || 13:00 || 21:30 || 8 ||  
 +
*details about experiment 1:
 +
  hidden_size = 700
 +
  emb_size = 510
 +
  learning_rate = 0.0005 (0.001 in prior)
 +
  small data,
 +
  2nd translator uses as training data the concat(Chinese, machine translated English),
 +
  2nd translator uses '''random initialized embedding'''
 +
*results (BLEU):
 +
  BASELINE: 43.87
 +
  best result of our model: '''42.19'''
 +
  Overfitting? In overall, the 2nd translator performs worse than baseline
 +
*details about experiment 2:
 +
  hidden_size = 500
 +
  emb_size = 310
 +
  learning_rate = 0.001
 +
  small data,
 +
  double-decoder model with joint loss which means the final loss  = 1st decoder's loss + 2nd
 +
  decoder's loss
 +
*results (BLEU):
 +
  BASELINE: 43.87
 +
  best result of our model: '''39.04'''
 +
  The 1st decoder's output is generally better than 2nd decoder's output. The reason may be that
 +
  the second decoder only learns from the first decoder's hidden states because their states are
 +
  almost the same.
 +
*DISCOVERY:
 +
  The reason why double-decoder without joint loss generalizes very bad is that the gap between
 +
  force teaching mechanism (training process) and beam search mechanism (decoding process)
 +
  propagates and expands the error to the output end, which destroys the model when decoding.
 +
*next:
 +
  Try to train double-decoder model without joint loss but with beam search on 1st decoder.
 
|-
 
|-
−
| rowspan="5"|2016/10/19
+
| rowspan="1"|2017/05/24
−
|Ziwei Bai || ||   || ||
+
|Aodong Li || 13:00 || 21:30 || 8 ||  
 +
*code double-attention one-decoder model
 +
*code double-decoder model
 
|-
 
|-
−
|Andy Zhang||9:30 || 19:00||8+ || read source code of seq2seq
+
 
 +
| rowspan="1"|2017/05/24
 +
|Shipan Ren || 10:00 || 20:00 || 10 ||  
 +
*read neural machine translation paper
 +
*read tf_translate code  
 
|-
 
|-
−
|Shiyue Zhang || 9:40 || 19:40 || 8+ ||
+
 
−
* finished reading MemNN code
+
| rowspan="2"|2017/05/25
−
* discussed the code with Teacher Feng
+
|Shipan Ren || 9:30 || 18:30 || 9 ||  
 +
*write document of tf_translate project
 +
*read neural machine translation paper
 +
*read tf_translate code  
 
|-
 
|-
−
|Aodong Li || ||   || ||
+
|Aodong Li || 13:00 || 22:00 || 9 ||  
 +
* code and debug double attention model
 
|-
 
|-
−
|Shiyao Li || || || ||  
+
 
 +
| rowspan="1"|2017/05/27
 +
|Shipan Ren || 9:30 || 18:30 || 9 ||
 +
*read tf_translate code
 +
*write document of tf_translate project
 
|-
 
|-
−
| rowspan="5"|2016/10/20
+
| rowspan="1"|2017/05/28
−
|Ziwei Bai ||||   || ||
+
|Aodong Li || 15:00 || 22:00 || 7 ||  
 +
*details about experiment:
 +
  hidden_size = 500
 +
  emb_size = 310
 +
  learning_rate = 0.001
 +
  small data,
 +
  2nd translator uses as training data both Chinese and machine translated English
 +
  Chinese and English use different encoders and different attention
 +
  '''final_attn = attn_1 + attn_2'''
 +
  2nd translator uses '''random initialized embedding'''
 +
*results (BLEU):
 +
  BASELINE: 43.87
 +
  when decoding:
 +
    final_attn = attn_1 + attn_2 best result of our model: '''43.50'''
 +
    final_attn = 2/3attn_1 + 4/3attn_2 best result of our model: '''41.22'''
 +
    final_attn = 4/3attn_1 + 2/3attn_2 best result of our model: '''43.58'''
 
|-
 
|-
−
|Andy Zhang||9:30 || 19:00||8+ || read source code of NTM
+
| rowspan="1"|2017/05/30
 +
|Aodong Li || 15:00 || 21:00 || 6 ||  
 +
*details about experiment 1:
 +
  hidden_size = 500
 +
  emb_size = 310
 +
  learning_rate = 0.001
 +
  small data,
 +
  2nd translator uses as training data both Chinese and machine translated English
 +
  Chinese and English use different encoders and different attention
 +
  '''final_attn = 2/3attn_1 + 4/3attn_2'''
 +
  2nd translator uses '''random initialized embedding'''
 +
*results (BLEU):
 +
  BASELINE: 43.87
 +
  best result of our model: '''42.36'''
 +
* details about experiment 2:
 +
  '''final_attn = 2/3attn_1 + 4/3attn_2'''
 +
  2nd translator uses '''constant initialized embedding'''
 +
*results (BLEU):
 +
  BASELINE: 43.87
 +
  best result of our model: '''45.32'''
 +
* details about experiment 3:
 +
  '''final_attn = attn_1 + attn_2'''
 +
  2nd translator uses '''constant initialized embedding'''
 +
*results (BLEU):
 +
  BASELINE: 43.87
 +
  best result of our model: '''45.41''' and it seems more stable
 
|-
 
|-
−
|Shiyue Zhang || || || ||  
+
| rowspan="2"|2017/05/31
 +
|Shipan Ren || 10:00 || 19:30 || 9.5 ||
 +
*run and test tf_translate code
 +
*write document of tf_translate project
 
|-
 
|-
−
|Aodong Li || ||   || ||
+
|Aodong Li || 12:00 || 20:30 || 8.5 ||  
 +
* details about experiment 1:
 +
  '''final_attn = 4/3attn_1 + 2/3attn_2'''
 +
  2nd translator uses '''constant initialized embedding'''
 +
*results (BLEU):
 +
  BASELINE: 43.87
 +
  best result of our model: '''45.79'''
 +
* That only make English word embedding at encoder constant and train all the other embedding and parameters achieves an even higher bleu score 45.98 and the results are stable.
 +
* The quality of English embedding at encoder plays an pivotal role in this model.
 +
* Preparation of big data.
 
|-
 
|-
−
|Shiyao Li || || || ||  
+
| rowspan="1"|2017/06/01
 +
|Aodong Li || 13:00 || 24:00 || 11 ||  
 +
* Only make the English encoder's embedding constant -- 45.98
 +
* Only initialize the English encoder's embedding and then finetune it -- 46.06
 +
* Share the attention mechanism and then directly add them -- 46.20
 +
* Run double-attention model on large data
 
|-
 
|-
−
| rowspan="5"|2016/10/21
+
| rowspan="1"|2017/06/02
−
|Ziwei Bai || 10:00|| 21:00 || 10 ||
+
|Aodong Li || 13:00 || 22:00 || 9 ||  
−
*Research news site
+
* Baseline bleu on large data is 30.83 with '''30000''' output vocab
 +
* Our best result is 31.53 with '''20000''' output vocab
 
|-
 
|-
−
|Andy Zhang|| || || ||  
+
| rowspan="1"|2017/06/03
 +
|Aodong Li || 13:00 || 21:00 || 8 ||
 +
* Train the model with 40 batch size and with concat(attn_1, attn_2)
 +
* the best result of model with 40 batch size and with add(attn_1, attn_2) is 30.52
 
|-
 
|-
−
|Shiyue Zhang || 9:30|| 20:00|| 8+||  
+
| rowspan="1"|2017/06/05
 +
|Aodong Li || 10:00 || 19:00 || 8 ||  
 +
* Prepare for APSIPA paper
 
|-
 
|-
−
|Aodong Li || ||   || ||
+
| rowspan="1"|2017/06/06
 +
|Aodong Li || 10:00 || 19:00 || 8 ||  
 +
* Prepare for APSIPA paper
 
|-
 
|-
−
|Shiyao Li || || || ||  
+
| rowspan="1"|2017/06/07
 +
|Aodong Li || 10:00 || 19:00 || 8 ||  
 +
* Prepare for APSIPA paper
 
|-
 
|-
−
| rowspan="5"|2016/10/22
+
| rowspan="1"|2017/06/08
−
|Ziwei Bai ||10:30 || 23:40  || 12 ||
+
|Aodong Li || 10:00 || 19:00 || 8 ||  
−
*Research news site
+
* Prepare for APSIPA paper
 
|-
 
|-
−
|Andy Zhang|| || || ||  
+
| rowspan="1"|2017/06/09
 +
|Aodong Li || 10:00 || 19:00 || 8 ||
 +
* Prepare for APSIPA paper
 
|-
 
|-
−
|Shiyue Zhang || || || ||  
+
| rowspan="1"|2017/06/12
 +
|Aodong Li || 10:00 || 19:00 || 8 ||
 +
* Prepare for APSIPA paper
 
|-
 
|-
−
|Aodong Li || ||   || ||
+
| rowspan="1"|2017/06/13
 +
|Aodong Li || 10:00 || 19:00 || 8 ||  
 +
* Prepare for APSIPA paper
 
|-
 
|-
−
|Shiyao Li || || || ||  
+
| rowspan="1"|2017/06/14
 +
|Aodong Li || 10:00 || 19:00 || 8 ||  
 +
* Prepare for APSIPA paper
 
|-
 
|-
−
| rowspan="5"|2016/10/23
+
| rowspan="1"|2017/06/15
−
|Ziwei Bai ||10:30 || 21:00 || 9.5 ||
+
|Aodong Li || 10:00 || 19:00 || 8 ||  
−
*Research news site
+
* Prepare for APSIPA paper
 +
* Read paper about MT involving grammar
 
|-
 
|-
−
|Andy Zhang|| || || ||  
+
| rowspan="1"|2017/06/16
 +
|Aodong Li || 10:00 || 19:00 || 8 ||
 +
* Prepare for APSIPA paper
 +
* Read paper about MT involving grammar
 
|-
 
|-
−
|Shiyue Zhang || || || ||  
+
| rowspan="1"|2017/06/19
 +
|Aodong Li || 10:00 || 19:00 || 8 ||
 +
* Completed APSIPA paper
 +
* Took new task in style translation
 
|-
 
|-
−
|Aodong Li || ||   || ||
+
| rowspan="1"|2017/06/20
 +
|Aodong Li || 10:00 || 19:00 || 8 ||  
 +
* Tried synonyms substitution
 
|-
 
|-
−
|Shiyao Li || || || ||  
+
| rowspan="1"|2017/06/21
 +
|Aodong Li || 10:00 || 19:00 || 8 ||  
 +
* Tried post edit like synonyms substitution but this didn't work
 
|-
 
|-
−
| rowspan="5"|2016/10/24
+
| rowspan="1"|2017/06/22
−
|Ziwei Bai  ||10:30 || 21:00 || 9.5 ||
+
|Aodong Li || 10:00 || 19:00 || 8 ||  
−
*Research news site
+
* Trained a GRU language model to determine similar word
 
|-
 
|-
−
|Andy Zhang||9:30 ||19:00 || 8+||  
+
| rowspan="2"|2017/06/23
−
*install deps for theano & blocks
+
|Shipan Ren || 10:00 || 21:00 || 11 ||  
−
*ran the attention code
+
* read neural machine translation paper
 +
* read and run tf_translate code  
 
|-
 
|-
−
|Shiyue Zhang || 9:30|| 20:30|| 9 ||
+
|Aodong Li || 10:00 || 19:00 || 8 ||  
−
* write the pipeline of generative model  
+
* Trained a GRU language model to determine similar word
−
* meeting
+
* This didn't work because semantics is not captured
 
|-
 
|-
−
|Aodong Li || ||   || ||
+
| rowspan="2"|2017/06/26
 +
|Shipan Ren || 10:00 || 21:00 || 11 ||
 +
* read paper：LSTM Neural Networks for Language Modeling
 +
* read and run ViVi_NMT code
 
|-
 
|-
−
|Shiyao Li || || || ||  
+
|Aodong Li || 10:00 || 19:00 || 8 ||  
 +
* Tried to figure out new ways to change the text style
 
|-
 
|-
−
| rowspan="5"|2016/10/25
+
| rowspan="2"|2017/06/27
−
|Ziwei Bai ||10:30 || 21:00 || 9.5 ||
+
|Shipan Ren || 10:00 || 20:00 || 10 ||  
−
*build crawling process for QA
+
* read the API of tensorflow
 +
* debugged ViVi_NMT and tried to upgrade code version to tensorflow1.0
 
|-
 
|-
−
|Andy Zhang||9:30 ||19:00 || 8+|| read the source code
+
|Aodong Li || 10:00 || 19:00 || 8 ||  
 +
* Trained seq2seq model to solve this problem
 +
* Semantics are stored in fixed-length vectors by a encoder and a decoder generate sequences on this vector
 
|-
 
|-
−
|Shiyue Zhang ||9:30 || 19:30 || 8+ ||  
+
| rowspan="2"|2017/06/28
−
* read the code cnn and write doc
+
|Shipan Ren || 10:00 || 19:00 || 9 ||  
 +
* debugged ViVi_NMT and tried to upgrade code version to tensorflow1.0 (on server)
 +
* installed tensorflow0.1 and tensorflow1.0 on my pc and debugged ViVi_NMT
 
|-
 
|-
−
|Aodong Li || ||   || ||
+
|Aodong Li || 10:00 || 19:00 || 8 ||  
 +
* Cross-domain seq2seq w/o attention and w/ attention models didn't work because of overfitting
 
|-
 
|-
−
|Shiyao Li || || || ||  
+
| rowspan="2"|2017/06/29
 +
|Shipan Ren || 10:00 || 20:00 || 10 ||
 +
* read the API of tensorflow
 +
* debugged ViVi_NMT and tried to upgrade code version to tensorflow1.0 (on server)
 
|-
 
|-
−
| rowspan="5"|2016/10/26
+
|Aodong Li || 10:00 || 19:00 || 8 ||  
−
|Ziwei Bai  ||10:30 || 21:00 || 9.5 ||
+
* Read style transfer papers
−
*build crawling process for news
+
 
|-
 
|-
−
|Andy Zhang||9:30 ||19:00 || 8+|| read the source code
+
| rowspan="2"|2017/06/30
 +
|Shipan Ren || 10:00 || 24:00 || 14 ||  
 +
* debugged ViVi_NMT and tried to upgrade code version to tensorflow1.0 (on server)
 +
* accomplished this task
 +
* found the new version saves more time，has lower complexity and better bleu than before
 
|-
 
|-
−
|Shiyue Zhang || || || ||  
+
|Aodong Li || 10:00 || 19:00 || 8 ||  
 +
* Read style transfer papers
 
|-
 
|-
−
|Aodong Li || ||   || ||
+
| rowspan="1"|2017/07/03
 +
|Shipan Ren || 9:00 || 21:00 || 12 ||
 +
* run two versions of the code on small data sets (Chinese-English)
 +
* tested these checkpoint
 +
 
 
|-
 
|-
−
|Shiyao Li || || || ||  
+
| rowspan="1"|2017/07/04
 +
|Shipan Ren || 9:00 || 21:00 || 12 ||
 +
* recorded experimental results
 +
* found version 1.0 of the code save more training time, has less complexity and these two version of the code has a similar Bleu value
 +
* found that the Bleu is still good when the model is over fitting
 +
* reason: the test set and training set are similar in content and style on small data set
 +
 
 
|-
 
|-
−
| rowspan="5"|2016/10/27
+
| rowspan="1"|2017/07/05
−
|Ziwei Bai  ||10:30 || 21:00 || 9.5 ||
+
|Shipan Ren || 9:00 || 21:00 || 12 ||  
−
*Training word vector
+
* run two versions of the code on big data sets (Chinese-English)
−
*cut word
+
* read NMT papers
 +
 
 
|-
 
|-
−
|Andy Zhang||9:30 ||19:00 || 8+|| read the source code
+
| rowspan="1"|2017/07/06
 +
|Shipan Ren || 9:00 || 21:00 || 12 ||  
 +
* out of memory（OOM） error occurred when version 0.1 of code was trained using large data set，but version 1.0 worked
 +
* reason: improper distribution of resources by the tensorflow0.1 version leads to exhaustion of memory resources
 +
* I've tried many times, and version 0.1 worked
 
|-
 
|-
−
|Shiyue Zhang || || || ||  
+
| rowspan="1"|2017/07/07
 +
|Shipan Ren || 9:00 || 21:00 || 12 ||
 +
* tested these checkpoints and recorded experimental results
 +
* the version 1.0 code saved 0.06 second per step than the version 0.1 code
 
|-
 
|-
−
|Aodong Li || ||   || ||
+
| rowspan="1"|2017/07/08
 +
|Shipan Ren || 9:00 || 21:00 || 12 ||
 +
* downloaded the wmt2014 data set
 +
* used the English-French data set to run the code and found the translation is not good
 +
* reason:no data preprocessing is done
 +
 
 
|-
 
|-
−
|Shiyao Li || || || ||  
+
| rowspan="1"|2017/07/10
 +
|Shipan Ren || 9:00 || 20:00 || 11 ||
 +
* trained translation models using tf1.0 baseline and tf0.1 baseline perspectively
 +
* dataset：zh-en small
 
|-
 
|-
−
| rowspan="5"|2016/10/28
+
| rowspan="1"|2017/07/11
−
|Ziwei Bai ||10:30 || 21:00 || 9.5 ||
+
|Shipan Ren || 9:00 || 20:00 || 11 ||  
−
*solve the memory error problem
+
* tested these checkpoints
 +
* found the new version takes less time
 +
* found these two versions have similar complexity and bleu values
 +
* found that the bleu is still good when the model is over fitting .
 +
* (reason: the test set and the train set of small data set are similar in content and style)
 +
 
 
|-
 
|-
−
|Andy Zhang|| || || ||
+
| rowspan="1"|2017/07/12
 +
|Shipan Ren || 9:00 || 20:00 || 11 ||
 +
* trained translation models using tf1.0 baseline and tf0.1 baseline perspectively
 +
* dataset：zh-en big
 +
 
 
|-
 
|-
−
|Shiyue Zhang || 9:15|| 19:30|| 9 ||  
+
| rowspan="1"|2017/07/13
−
* write rnng&cnn document
+
|Shipan Ren || 9:00 || 20:00 || 11 ||  
 +
* OOM（Out Of Memory） error occurred when version 0.1 was trained using large data set，but version 1.0 worked
 +
    reason: improper distribution of resources by the tensorflow0.1 frame leads to exhaustion of memory resources
 +
* I had tried 4 times （just enter the same command）, and version 0.1 worked
 +
 
 
|-
 
|-
−
|Aodong Li || ||   || ||
+
| rowspan="1"|2017/07/14
 +
|Shipan Ren || 9:00 || 20:00 || 11 ||
 +
* tested these checkpoints
 +
* found the new version takes less time
 +
* found these two versions have similar complexity and bleu values
 +
 
 
|-
 
|-
−
|Shiyao Li || || || ||  
+
| rowspan="1"|2017/07/17
 +
|Shipan Ren || 9:00 || 20:00 || 11 ||
 +
* downloaded the wmt2014 data sets and processed it
 +
 
 
|-
 
|-
−
| rowspan="5"|2016/10/31
+
| rowspan="1"|2017/07/18
−
|Ziwei Bai || ||   || ||
+
|Shipan Ren || 9:00 || 20:00 || 11 ||  
 +
* processed data
 +
 
 
|-
 
|-
−
|Andy Zhang|| || || ||
+
| rowspan="1"|2017/07/18
 +
|Jiayu Guo || 8:30|| 22:00 || 14 ||
 +
* read model code.
 +
 
 
|-
 
|-
−
|Shiyue Zhang || 9:15 || 20:30|| 9+||
+
| rowspan="1"|2017/07/19
−
* finish the document writing
+
|Shipan Ren || 9:00 || 20:00 || 11 ||  
−
* try to add memory in rnng
+
* processed data
 
|-
 
|-
−
|Aodong Li || ||   || ||
+
| rowspan="1"|2017/07/19
 +
|Jiayu Guo || 9:00|| 22:00 || 13 ||
 +
* read papers of bleu.
 
|-
 
|-
−
|Shiyao Li || || || ||  
+
| rowspan="1"|2017/07/20
 +
|Shipan Ren || 9:00 || 20:00 || 11 ||
 +
* processed data
 
|-
 
|-
−
| rowspan="5"|2016/11/1
+
| rowspan="1"|2017/07/20
−
|Ziwei Bai || 14:30 || 19:30  || 5 ||  
+
|Jiayu Guo || 9:00|| 22:00 || 13 ||
−
*resplit the train data
+
* read papers of attention mechanism.
 
|-
 
|-
−
|Andy Zhang|| || || ||
+
| rowspan="1"|2017/07/21
 +
|Shipan Ren || 9:00 || 20:00 || 11 ||
 +
* trained translation models using tf1.0 baseline and tf0.1 baseline perspectively
 +
* dataset:WMT2014 en-de
 
|-
 
|-
−
|Shiyue Zhang || 9:15 || 19:30|| 8||
+
| rowspan="1"|2017/07/21
−
* finish a simple way to add memory into rnng and write a report
+
|Jiayu Guo || 10:00|| 23:00 || 13 ||
−
* meeting
+
* process document
 +
 
 
|-
 
|-
−
|Aodong Li || ||   || ||
+
| rowspan="1"|2017/07/24
 +
|Shipan Ren || 9:00 || 20:00 || 11 ||
 +
* tested these checkpoints of en-de dataset
 +
* found the new version takes less time
 +
* found these two versions have similar complexity and bleu values
 +
 
 
|-
 
|-
−
|Shiyao Li || || || ||  
+
| rowspan="1"|2017/07/24
−
|}
+
|Jiayu Guo || 9:00|| 22:00 || 13 ||
 +
* read model code.
 +
|-
 +
| rowspan="1"|2017/07/25
 +
|Shipan Ren || 9:00 || 20:00 || 11 ||
 +
* trained translation models using tf1.0 baseline and tf0.1 baseline perspectively
 +
* dataset:WMT2014 en-fr datasets
 +
|-
 +
| rowspan="1"|2017/07/25
 +
|Jiayu Guo || 9:00|| 23:00 || 14 ||
 +
* process document
  
−
===Monthly Summary===
+
|-
 +
| rowspan="1"|2017/07/26
 +
|Shipan Ren || 9:00 || 20:00 || 11 ||
 +
* read papers about memory-augmented nmt
  
−
{| class="wikitable"
 
−
!People!! Summary
 
 
|-
 
|-
−
|Yang Feng ||  
+
| rowspan="1"|2017/07/26
 +
|Jiayu Guo || 10:00|| 24:00 || 14 ||
 +
* process document
 +
 
 
|-
 
|-
−
|Jiyuan Zhang ||  
+
| rowspan="1"|2017/07/27
 +
|Shipan Ren || 9:00 || 20:00 || 11 ||
 +
* read papers about memory-augmented nmt
 +
 
 
|-
 
|-
−
|Aodong Li ||  
+
| rowspan="1"|2017/07/27
 +
|Jiayu Guo || 10:00|| 24:00 || 14 ||
 +
* process document
 +
 
 
|-
 
|-
−
|Ziwei Bai ||  
+
| rowspan="1"|2017/07/28
 +
|Shipan Ren || 9:00 || 20:00 || 11 ||
 +
* read memory-augmented nmt code
 +
 
 
|-
 
|-
−
|Andy Zhang ||  
+
| rowspan="1"|2017/07/28
 +
|Jiayu Guo || 9:00|| 24:00 || 15 ||
 +
* process document
 +
|
 +
 
 
|-
 
|-
−
|Shiyao Li ||  
+
| rowspan="1"|2017/07/31
 +
|Shipan Ren || 9:00 || 20:00 || 11 ||
 +
* read memory-augmented nmt code
 
|-
 
|-
−
|Shiyue Zhang ||
+
| rowspan="1"|2017/07/31
−
|}
+
|Jiayu Guo || 10:00|| 23:00 || 13 ||
 +
* split ancient language text to single word
 +
|
 +
|-
 +
| rowspan="1"|2017/08/1
 +
|Shipan Ren || 9:00 || 20:00 || 11 ||
 +
* tested these checkpoints of en-fr dataset
 +
* found the new version takes less time
 +
* found these two versions have similar complexity and bleu values
 +
|-
 +
| rowspan="1"|2017/08/1
 +
|Jiayu Guo || 10:00|| 23:00 || 13 ||
 +
* run seq2seq_model
 +
|
 +
|-
 +
| rowspan="1"|2017/08/2
 +
|Shipan Ren || 9:00 || 20:00 || 11 ||
 +
* looked for the performance(the bleu value) of other models
 +
* datasets:WMT2014 en-de and en-fr
 +
 
 +
|-
 +
| rowspan="1"|2017/08/2
 +
|Jiayu Guo || 10:00|| 23:00 || 13 ||
 +
* process document
 +
|-
 +
| rowspan="1"|2017/08/3
 +
|Shipan Ren || 9:00 || 20:00 || 11 ||
 +
* looked for the performance(the bleu value) of other seq2seq models
 +
* datasets:WMT2014 en-de and en-fr
 +
 
 +
|-
 +
| rowspan="1"|2017/08/3
 +
|Jiayu Guo || 10:00|| 23:00 || 13 ||
 +
* process document
 +
|-
 +
| rowspan="1"|2017/08/4
 +
|Shipan Ren || 9:00 || 20:00 || 11 ||
 +
* learn moses
 +
 
 +
|-
 +
| rowspan="1"|2017/08/4
 +
|Jiayu Guo || 10:00|| 23:00 || 13 ||
 +
* search new data(Songshu)
 +
 
 +
|-
 +
| rowspan="1"|2017/08/7
 +
|Shipan Ren || 9:00 || 20:00 || 11 ||
 +
* installed and built Moses on the server
 +
 
 +
|-
 +
| rowspan="1"|2017/08/7
 +
|Jiayu Guo || 9:00|| 22:00 || 13 ||
 +
* process document
 +
 
 +
|-
 +
| rowspan="1"|2017/08/8
 +
|Shipan Ren || 9:00 || 20:00 || 11 ||
 +
* train statistical machine translation model and test it
 +
* dataset:zh-en small
 +
* test if moses can work normally
 +
 
 +
|-
 +
| rowspan="1"|2017/08/8
 +
|Jiayu Guo || 10:00|| 21:00 || 11 ||
 +
* read tensorflow
 +
 
 +
|-
 +
| rowspan="1"|2017/08/9
 +
|Shipan Ren || 9:00 || 20:00 || 11 ||
 +
* code automation scripts to process data,train model and test model
 +
* toolkit: Moses
 +
 
 +
|-
 +
| rowspan="1"|2017/08/9
 +
|Jiayu Guo || 10:00|| 23:00 || 13 ||
 +
* run model with the data of which ancient content was split by single character.
 +
 
 +
|-
 +
| rowspan="1"|2017/08/10
 +
|Shipan Ren || 9:00 || 20:00 || 11 ||
 +
* train statistical machine translation models and test it
 +
* dataset:zh-en big,WMT2014 en-de,WMT2014 en-fr
 +
 
 +
|-
 +
| rowspan="1"|2017/08/10
 +
|Jiayu Guo || 9:00|| 23:00 || 13 ||
 +
* process data of Songshu
 +
* read papers of CNN
 +
 
 +
|-
 +
| rowspan="1"|2017/08/11
 +
|Shipan Ren || 9:00 || 20:00 || 11 ||
 +
* collate experimental results
 +
* compare our baseline model with Moses
 +
 
 +
|-
 +
| rowspan="1"|2017/08/11
 +
|Jiayu Guo || 9:00|| 20:00 || 11 ||
 +
* test results.
 +
 
 +
|-
 +
 
 +
| rowspan="1"|2017/08/14
 +
|Shipan Ren || 9:00 || 20:00 || 11 ||
 +
* read paper about THUMT
 +
|-
 +
| rowspan="1"|2017/08/14
 +
|Jiayu Guo || 10:00|| 23:00 || 13 ||
 +
* learn about Graphic Model of LSTM-Projected BPTT
 +
* search for data available for translation (Twenty-four-Shi)
 +
|-
 +
 
 +
| rowspan="1"|2017/08/15
 +
|Shipan Ren || 9:00 || 20:00 || 11 ||
 +
* read THUMT manual and learn how to use it
 +
|-
 +
| rowspan="1"|2017/08/15
 +
|Jiayu Guo || 11:00|| 23:30 || 12 ||
 +
* run model with data including Shiji、Zizhitongjian.
 +
|-
 +
| rowspan="1"|2017/08/16
 +
|Shipan Ren || 9:00 || 20:00 || 11 ||
 +
* train translation models and test them
 +
* toolkit: THUMT
 +
* dataset:zh-en small
 +
* test if THUMT can work normally
 +
 
 +
|-
 +
| rowspan="1"|2017/08/16
 +
|Jiayu Guo || 10:00|| 23:00 || 10||
 +
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。
 +
 
 +
*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.
 +
|-
 +
 
 +
| rowspan="1"|2017/08/17
 +
|Shipan Ren || 9:00 || 20:00 || 11 ||
 +
* code automation scripts to process data,train model and test model
 +
* train translation models and test them
 +
* toolkit: THUMT
 +
* dataset:zh-en big
 +
 
 +
|-
 +
| rowspan="1"|2017/08/17
 +
|Jiayu Guo || 13:00|| 23:00 || 10 ||
 +
* read source code.
 +
|-
 +
| rowspan="1"|2017/08/18
 +
|Shipan Ren || 9:00 || 20:00 || 11 ||
 +
* test translation models by using single reference and  multiple reference
 +
* organize all the experimental results(our baseline system,Moses,THUMT)
 +
 
 +
|-
 +
| rowspan="1"|2017/08/18
 +
|Jiayu Guo || 13:00|| 22:00 || 9 ||
 +
* read source code.
 +
|-
 +
| rowspan="1"|2017/08/21
 +
|Shipan Ren || 10:00 || 22:00 || 12 ||
 +
* read the released information of other translation systems
 +
|-
 +
| rowspan="1"|2017/08/21
 +
|Jiayu Guo || 9:30 || 21:30 || 12 ||
 +
* read the source code and learn tensorflow
 +
|-
 +
| rowspan="1"|2017/08/22
 +
|Shipan Ren || 10:00 || 22:00 || 12 ||
 +
* cleaned up the code
 +
|-
 +
| rowspan="1"|2017/08/22
 +
|Jiayu Guo || 9:00 || 22:00 || 12 ||
 +
* read the source code
 +
|-
 +
| rowspan="1"|2017/08/23
 +
|Shipan Ren || 10:00 || 21:00 || 11 ||
 +
* wrote the documents
 +
|-
 +
| rowspan="1"|2017/08/23
 +
|Jiayu Guo || 9:00 || 22:00 || 11 ||
 +
* read the source code and learn tensorflow
 +
|-
 +
| rowspan="1"|2017/08/24
 +
|Shipan Ren || 10:00 || 20:00 || 10 ||
 +
* wrote the documents
 +
|-
 +
| rowspan="1"|2017/08/24
 +
|Jiayu Guo || 9:10 || 22:00 || 10.5 ||
 +
* read the source code and learn tensorflow
 +
|-
 +
| rowspan="1"|2017/08/25
 +
|Shipan Ren || 10:00 || 20:00 || 10 ||
 +
* check experimental results
 +
|-
 +
| rowspan="1"|2017/08/25
 +
|Jiayu Guo || 8:50 || 22:00 || 10.5 ||
 +
* read the source code and learn tensorflow
 +
|-
 +
| rowspan="1"|2017/08/28
 +
|Shipan Ren || 10:00 || 20:00 || 10 ||
 +
* wrote the paper of ViVi_NMT(version 1.0)
 +
|-
 +
| rowspan="1"|2017/08/28
 +
|Jiayu Guo || 8:10 || 21:00 || 11 ||
 +
* read the source code and learn tensorflow
 +
|-
 +
| rowspan="1"|2017/08/29
 +
|Shipan Ren || 10:00 || 20:00 || 10 ||
 +
* wrote the paper of ViVi_NMT(version 1.0)
 +
|-
 +
| rowspan="1"|2017/08/29
 +
|Jiayu Guo || 11:00 || 21:00 || 10 ||
 +
* read the source code and learn tensorflow
 +
|-
 +
| rowspan="1"|2017/08/30
 +
|Shipan Ren || 10:00 || 20:00 || 10 ||
 +
* wrote the paper of ViVi_NMT(version 1.0)
 +
|-
 +
| rowspan="1"|2017/08/30
 +
|Jiayu Guo || 11:30 || 21:00 || 9 ||
 +
* learn VV model
 +
|-
 +
| rowspan="1"|2017/08/31
 +
|Shipan Ren || 10:00 || 20:00 || 10 ||
 +
* wrote the paper of ViVi_NMT(version 1.0)
 +
|-
 +
| rowspan="1"|2017/08/31
 +
|Jiayu Guo || 10:00 || 20:00 || 10 ||
 +
* clean up the code
 +
|-
 +
}
  
 
===Time Off Table===
 
===Time Off Table===
第370行： 第969行：
 
! Date !! Yang Feng !! Jiyuan Zhang  
 
! Date !! Yang Feng !! Jiyuan Zhang  
 
|-
 
|-
−
|10/14 || 3h ||
 
−
|-
 
−
|10/20 || 3h ||
 
 
|}
 
|}
  
 
==Past progress==
 
==Past progress==
 +
[[nlp-progress 2017/03]]
 +
 +
[[nlp-progress 2017/02]]
 +
 +
[[nlp-progress 2017/01]]
 +
 +
[[nlp-progress 2016/12]]
 +
 +
[[nlp-progress 2016/11]]
 +
 +
[[nlp-progress 2016/10]]
 +
 
[[nlp-progress 2016/09]]
 
[[nlp-progress 2016/09]]
  

2017年9月4日 (一) 07:41的最后版本

NLP Schedule

Members

Current Members

  • Yang Feng (冯洋)
  • Jiyuan Zhang （张记袁）
  • Aodong Li (李傲冬)
  • Andi Zhang (张安迪)
  • Shiyue Zhang (张诗悦)
  • Li Gu (古丽)
  • Peilun Xiao (肖培伦)
  • Shipan Ren (任师攀)
  • Jiayu Guo (郭佳雨)

Former Members

  • Chao Xing (邢超)  : FreeNeb
  • Rong Liu (刘荣)  : 优酷
  • Xiaoxi Wang (王晓曦) : 图灵机器人
  • Xi Ma (马习)  : 清华大学研究生
  • Tianyi Luo (骆天一) ： phd candidate in University of California Santa Cruz
  • Qixin Wang (王琪鑫)  : MA candidate in University of California
  • DongXu Zhang (张东旭): --
  • Yiqiao Pan (潘一桥) ： MA candidate in University of Sydney
  • Shiyao Li （李诗瑶） : BUPT
  • Aiting Liu (刘艾婷)  : BUPT

Work Progress

Daily Report

}

Time Off Table

Date Person start leave hours status
2017/04/02 Andy Zhang 9:30 18:30 8
  • preparing EMNLP
Peilun Xiao
2017/04/03 Andy Zhang 9:30 18:30 8
  • preparing EMNLP
Peilun Xiao
2017/04/04 Andy Zhang 9:30 18:30 8
  • preparing EMNLP
Peilun Xiao
2017/04/05 Andy Zhang 9:30 18:30 8
  • preparing EMNLP
Peilun Xiao
2017/04/06 Andy Zhang 9:30 18:30 8
  • preparing EMNLP
Peilun Xiao
2017/04/07 Andy Zhang 9:30 18:30 8
  • preparing EMNLP
Peilun Xiao
2017/04/08 Andy Zhang 9:30 18:30 8
  • preparing EMNLP
Peilun Xiao
2017/04/09 Andy Zhang 9:30 18:30 8
  • preparing EMNLP
Peilun Xiao
2017/04/10 Andy Zhang 9:30 18:30 8
  • preparing EMNLP
Peilun Xiao
2017/04/11 Andy Zhang 9:30 18:30 8
  • preparing EMNLP
Peilun Xiao
2017/04/12 Andy Zhang 9:30 18:30 8
  • preparing EMNLP
Peilun Xiao
2017/04/13 Andy Zhang 9:30 18:30 8
  • preparing EMNLP
Peilun Xiao
2017/04/14 Andy Zhang 9:30 18:30 8
  • preparing EMNLP
Peilun Xiao
2017/04/15 Andy Zhang 9:00 15:00 6
  • preparing EMNLP
Peilun Xiao
2017/04/18 Aodong Li 11:00 20:00 8
  • Pick up new task in news generation and do literature review
2017/04/19 Aodong Li 11:00 20:00 8
  • Literature review
2017/04/20 Aodong Li 12:00 20:00 8
  • Literature review
2017/04/21 Aodong Li 12:00 20:00 8
  • Literature review
2017/04/24 Aodong Li 11:00 20:00 8
  • Adjust literature review focus
2017/04/25 Aodong Li 11:00 20:00 8
  • Literature review
2017/04/26 Aodong Li 11:00 20:00 8
  • Literature review
2017/04/27 Aodong Li 11:00 20:00 8
  • Try to reproduce sc-lstm work
2017/04/28 Aodong Li 11:00 20:00 8
  • Transfer to new task in machine translation and do literature review
2017/04/30 Aodong Li 11:00 20:00 8
  • Literature review
2017/05/01 Aodong Li 11:00 20:00 8
  • Literature review
2017/05/02 Aodong Li 11:00 20:00 8
  • Literature review and code review
2017/05/06 Aodong Li 14:20 17:20 3
  • Code review
2017/05/07 Aodong Li 13:30 22:00 8
  • Code review and experiment started, but version discrepancy encountered
2017/05/08 Aodong Li 11:30 21:00 8
  • Code review and version discrepancy solved
2017/05/09 Aodong Li 13:00 22:00 9
  • Code review and experiment
  • details about experiment: 
 small data, 
 1st and 2nd translator uses the same training data, 
 2nd translator uses random initialized embedding
  • results (BLEU): 
 BASELINE: 43.87
 best result of our model: 42.56
2017/05/10 Shipan Ren 9:00 20:00 11
  • Entry procedures
  • Machine Translation paper reading
2017/05/10 Aodong Li 13:30 22:00 8
  • experiment setting: 
 small data, 
 1st and 2nd translator uses the different training data, counting 22000 and 22017 seperately
 2nd translator uses random initialized embedding
  • results (BLEU): 
 BASELINE: 36.67 (36.67 is the model at 4750 updates, but we use model at 3000 updates to
                    prevent the case of overfitting, to generate the 2nd translator's training data, for 
                    which the BLEU is 34.96)
 best result of our model: 29.81
 This may suggest that that using either the same training data with 1st translator or different
                   one won't influence 2nd translator's performance, instead, using the same one may
                    be better, at least from results. But I have to give a consideration of a smaller size 
                    of training data compared to yesterday's model.
  • code 2nd translator with constant embedding
2017/05/11 Shipan Ren 10:00 19:30 9.5
  • Configure environment
  • Run tf_translate code
  • Read Machine Translation paper
2017/05/11 Aodong Li 13:00 21:00 8
  • experiment setting: 
 small data, 
 1st and 2nd translator uses the same training data, 
 2nd translator uses constant untrainable embedding imported from 1st translator's decoder
  • results (BLEU): 
 BASELINE: 43.87
 best result of our model: 43.48
 Experiments show that this kind of series or cascade model will definitely impair the final perfor-
                     mance due to information loss as the information flows through the network from 
                     end to end. Decoder's smaller vocabulary size compared to encoder's demonstrate
                     this (9000+ -> 6000+).
 The intention of this experiment is looking for a map to solve meaning shift using 2nd translator,
                     but result of whether the map is learned or not is obscured by the smaller vocab size 
                     phenomenon.
  • literature review on hierarchical machine translation
2017/05/12 Aodong Li 13:00 21:00 8
  • Code double decoding model and read multilingual MT paper
2017/05/13 Shipan Ren 10:00 19:00 9
  • read machine translation paper
  • learne lstm model and seq2seq model
2017/05/14 Aodong Li 10:00 20:00 9
  • Code double decoding model and experiment
  • details about experiment: 
 small data, 
 2nd translator uses as training data the concat(Chinese, machine translated English), 
 2nd translator uses random initialized embedding
  • results (BLEU): 
 BASELINE: 43.87
 best result of our model: 43.53
  • NEXT: 2nd translator uses trained constant embedding
2017/05/15 Shipan Ren 9:30 19:00 9.5
  • understand the difference between lstm model and gru model
  • read the implement code of seq2seq model
2017/05/17 Shipan Ren 9:30 19:30 10
  • read neural machine translation paper
  • read tf_translate code
Aodong Li 13:30 24:00 9
  • code and debug double-decoder model
  • alter 2017/05/14 model's size and will try after nips
2017/05/18 Shipan Ren 10:00 19:00 9
  • read neural machine translation paper
  • read tf_translate code
Aodong Li 12:30 21:00 8
  • train double-decoder model on small data set but encounter decode bugs
2017/05/19 Aodong Li 12:30 20:30 8
  • debug double-decoder model
  • the model performs well on develop set, but performs badly on test data. I want to figure out the reason.
2017/05/21 Aodong Li 10:30 18:30 8
  • details about experiment: 
 hidden_size = 700 (500 in prior)
 emb_size = 510 (310 in prior)
 small data, 
 2nd translator uses as training data the concat(Chinese, machine translated English), 
 2nd translator uses random initialized embedding
  • results (BLEU): 
 BASELINE: 43.87
 best result of our model: 45.21
 But only one checkpoint outperforms the baseline, the other results are commonly under 43.1
  • debug double-decoder model
2017/05/22 Aodong Li 14:00 22:00 8
  • double-decoder without joint loss generalizes very bad
  • i'm trying double-decoder model with joint loss
2017/05/23 Aodong Li 13:00 21:30 8
  • details about experiment 1: 
 hidden_size = 700
 emb_size = 510
 learning_rate = 0.0005 (0.001 in prior)
 small data, 
 2nd translator uses as training data the concat(Chinese, machine translated English), 
 2nd translator uses random initialized embedding
  • results (BLEU): 
 BASELINE: 43.87
 best result of our model: 42.19
 Overfitting? In overall, the 2nd translator performs worse than baseline
  • details about experiment 2: 
 hidden_size = 500
 emb_size = 310
 learning_rate = 0.001
 small data, 
 double-decoder model with joint loss which means the final loss  = 1st decoder's loss + 2nd 
 decoder's loss
  • results (BLEU): 
 BASELINE: 43.87
 best result of our model: 39.04
 The 1st decoder's output is generally better than 2nd decoder's output. The reason may be that 
 the second decoder only learns from the first decoder's hidden states because their states are 
 almost the same.
  • DISCOVERY: 
 The reason why double-decoder without joint loss generalizes very bad is that the gap between
 force teaching mechanism (training process) and beam search mechanism (decoding process)
 propagates and expands the error to the output end, which destroys the model when decoding.
  • next: 
 Try to train double-decoder model without joint loss but with beam search on 1st decoder.
2017/05/24 Aodong Li 13:00 21:30 8
  • code double-attention one-decoder model
  • code double-decoder model
2017/05/24 Shipan Ren 10:00 20:00 10
  • read neural machine translation paper
  • read tf_translate code
2017/05/25 Shipan Ren 9:30 18:30 9
  • write document of tf_translate project
  • read neural machine translation paper
  • read tf_translate code
Aodong Li 13:00 22:00 9
  • code and debug double attention model
2017/05/27 Shipan Ren 9:30 18:30 9
  • read tf_translate code
  • write document of tf_translate project
2017/05/28 Aodong Li 15:00 22:00 7
  • details about experiment: 
 hidden_size = 500
 emb_size = 310
 learning_rate = 0.001
 small data, 
 2nd translator uses as training data both Chinese and machine translated English
 Chinese and English use different encoders and different attention
 final_attn = attn_1 + attn_2
 2nd translator uses random initialized embedding
  • results (BLEU): 
 BASELINE: 43.87
 when decoding:
   final_attn = attn_1 + attn_2 best result of our model: 43.50
   final_attn = 2/3attn_1 + 4/3attn_2 best result of our model: 41.22
   final_attn = 4/3attn_1 + 2/3attn_2 best result of our model: 43.58
2017/05/30 Aodong Li 15:00 21:00 6
  • details about experiment 1: 
 hidden_size = 500
 emb_size = 310
 learning_rate = 0.001
 small data, 
 2nd translator uses as training data both Chinese and machine translated English
 Chinese and English use different encoders and different attention
 final_attn = 2/3attn_1 + 4/3attn_2
 2nd translator uses random initialized embedding
  • results (BLEU): 
 BASELINE: 43.87
 best result of our model: 42.36
  • details about experiment 2: 
 final_attn = 2/3attn_1 + 4/3attn_2
 2nd translator uses constant initialized embedding
  • results (BLEU): 
 BASELINE: 43.87
 best result of our model: 45.32
  • details about experiment 3: 
 final_attn = attn_1 + attn_2
 2nd translator uses constant initialized embedding
  • results (BLEU): 
 BASELINE: 43.87
 best result of our model: 45.41 and it seems more stable
2017/05/31 Shipan Ren 10:00 19:30 9.5
  • run and test tf_translate code
  • write document of tf_translate project
Aodong Li 12:00 20:30 8.5
  • details about experiment 1: 
 final_attn = 4/3attn_1 + 2/3attn_2
 2nd translator uses constant initialized embedding
  • results (BLEU): 
 BASELINE: 43.87
 best result of our model: 45.79
  • That only make English word embedding at encoder constant and train all the other embedding and parameters achieves an even higher bleu score 45.98 and the results are stable.
  • The quality of English embedding at encoder plays an pivotal role in this model.
  • Preparation of big data.
2017/06/01 Aodong Li 13:00 24:00 11
  • Only make the English encoder's embedding constant -- 45.98
  • Only initialize the English encoder's embedding and then finetune it -- 46.06
  • Share the attention mechanism and then directly add them -- 46.20
  • Run double-attention model on large data
2017/06/02 Aodong Li 13:00 22:00 9
  • Baseline bleu on large data is 30.83 with 30000 output vocab
  • Our best result is 31.53 with 20000 output vocab
2017/06/03 Aodong Li 13:00 21:00 8
  • Train the model with 40 batch size and with concat(attn_1, attn_2)
  • the best result of model with 40 batch size and with add(attn_1, attn_2) is 30.52
2017/06/05 Aodong Li 10:00 19:00 8
  • Prepare for APSIPA paper
2017/06/06 Aodong Li 10:00 19:00 8
  • Prepare for APSIPA paper
2017/06/07 Aodong Li 10:00 19:00 8
  • Prepare for APSIPA paper
2017/06/08 Aodong Li 10:00 19:00 8
  • Prepare for APSIPA paper
2017/06/09 Aodong Li 10:00 19:00 8
  • Prepare for APSIPA paper
2017/06/12 Aodong Li 10:00 19:00 8
  • Prepare for APSIPA paper
2017/06/13 Aodong Li 10:00 19:00 8
  • Prepare for APSIPA paper
2017/06/14 Aodong Li 10:00 19:00 8
  • Prepare for APSIPA paper
2017/06/15 Aodong Li 10:00 19:00 8
  • Prepare for APSIPA paper
  • Read paper about MT involving grammar
2017/06/16 Aodong Li 10:00 19:00 8
  • Prepare for APSIPA paper
  • Read paper about MT involving grammar
2017/06/19 Aodong Li 10:00 19:00 8
  • Completed APSIPA paper
  • Took new task in style translation
2017/06/20 Aodong Li 10:00 19:00 8
  • Tried synonyms substitution
2017/06/21 Aodong Li 10:00 19:00 8
  • Tried post edit like synonyms substitution but this didn't work
2017/06/22 Aodong Li 10:00 19:00 8
  • Trained a GRU language model to determine similar word
2017/06/23 Shipan Ren 10:00 21:00 11
  • read neural machine translation paper
  • read and run tf_translate code
Aodong Li 10:00 19:00 8
  • Trained a GRU language model to determine similar word
  • This didn't work because semantics is not captured
2017/06/26 Shipan Ren 10:00 21:00 11
  • read paper：LSTM Neural Networks for Language Modeling
  • read and run ViVi_NMT code
Aodong Li 10:00 19:00 8
  • Tried to figure out new ways to change the text style
2017/06/27 Shipan Ren 10:00 20:00 10
  • read the API of tensorflow
  • debugged ViVi_NMT and tried to upgrade code version to tensorflow1.0
Aodong Li 10:00 19:00 8
  • Trained seq2seq model to solve this problem
  • Semantics are stored in fixed-length vectors by a encoder and a decoder generate sequences on this vector
2017/06/28 Shipan Ren 10:00 19:00 9
  • debugged ViVi_NMT and tried to upgrade code version to tensorflow1.0 (on server)
  • installed tensorflow0.1 and tensorflow1.0 on my pc and debugged ViVi_NMT
Aodong Li 10:00 19:00 8
  • Cross-domain seq2seq w/o attention and w/ attention models didn't work because of overfitting
2017/06/29 Shipan Ren 10:00 20:00 10
  • read the API of tensorflow
  • debugged ViVi_NMT and tried to upgrade code version to tensorflow1.0 (on server)
Aodong Li 10:00 19:00 8
  • Read style transfer papers
2017/06/30 Shipan Ren 10:00 24:00 14
  • debugged ViVi_NMT and tried to upgrade code version to tensorflow1.0 (on server)
  • accomplished this task
  • found the new version saves more time，has lower complexity and better bleu than before
Aodong Li 10:00 19:00 8
  • Read style transfer papers
2017/07/03 Shipan Ren 9:00 21:00 12
  • run two versions of the code on small data sets (Chinese-English)
  • tested these checkpoint
2017/07/04 Shipan Ren 9:00 21:00 12
  • recorded experimental results
  • found version 1.0 of the code save more training time, has less complexity and these two version of the code has a similar Bleu value
  • found that the Bleu is still good when the model is over fitting
  • reason: the test set and training set are similar in content and style on small data set
2017/07/05 Shipan Ren 9:00 21:00 12
  • run two versions of the code on big data sets (Chinese-English)
  • read NMT papers
2017/07/06 Shipan Ren 9:00 21:00 12
  • out of memory（OOM） error occurred when version 0.1 of code was trained using large data set，but version 1.0 worked
  • reason: improper distribution of resources by the tensorflow0.1 version leads to exhaustion of memory resources
  • I've tried many times, and version 0.1 worked
2017/07/07 Shipan Ren 9:00 21:00 12
  • tested these checkpoints and recorded experimental results
  • the version 1.0 code saved 0.06 second per step than the version 0.1 code
2017/07/08 Shipan Ren 9:00 21:00 12
  • downloaded the wmt2014 data set
  • used the English-French data set to run the code and found the translation is not good
  • reason:no data preprocessing is done
2017/07/10 Shipan Ren 9:00 20:00 11
  • trained translation models using tf1.0 baseline and tf0.1 baseline perspectively
  • dataset：zh-en small
2017/07/11 Shipan Ren 9:00 20:00 11
  • tested these checkpoints
  • found the new version takes less time
  • found these two versions have similar complexity and bleu values
  • found that the bleu is still good when the model is over fitting .
  • (reason: the test set and the train set of small data set are similar in content and style)
2017/07/12 Shipan Ren 9:00 20:00 11
  • trained translation models using tf1.0 baseline and tf0.1 baseline perspectively
  • dataset：zh-en big
2017/07/13 Shipan Ren 9:00 20:00 11
  • OOM（Out Of Memory） error occurred when version 0.1 was trained using large data set，but version 1.0 worked 
   reason: improper distribution of resources by the tensorflow0.1 frame leads to exhaustion of memory resources
  • I had tried 4 times （just enter the same command）, and version 0.1 worked
2017/07/14 Shipan Ren 9:00 20:00 11
  • tested these checkpoints
  • found the new version takes less time
  • found these two versions have similar complexity and bleu values
2017/07/17 Shipan Ren 9:00 20:00 11
  • downloaded the wmt2014 data sets and processed it
2017/07/18 Shipan Ren 9:00 20:00 11
  • processed data
2017/07/18 Jiayu Guo 8:30 22:00 14
  • read model code.
2017/07/19 Shipan Ren 9:00 20:00 11
  • processed data
2017/07/19 Jiayu Guo 9:00 22:00 13
  • read papers of bleu.
2017/07/20 Shipan Ren 9:00 20:00 11
  • processed data
2017/07/20 Jiayu Guo 9:00 22:00 13
  • read papers of attention mechanism.
2017/07/21 Shipan Ren 9:00 20:00 11
  • trained translation models using tf1.0 baseline and tf0.1 baseline perspectively
  • dataset:WMT2014 en-de
2017/07/21 Jiayu Guo 10:00 23:00 13
  • process document
2017/07/24 Shipan Ren 9:00 20:00 11
  • tested these checkpoints of en-de dataset
  • found the new version takes less time
  • found these two versions have similar complexity and bleu values
2017/07/24 Jiayu Guo 9:00 22:00 13
  • read model code.
2017/07/25 Shipan Ren 9:00 20:00 11
  • trained translation models using tf1.0 baseline and tf0.1 baseline perspectively
  • dataset:WMT2014 en-fr datasets
2017/07/25 Jiayu Guo 9:00 23:00 14
  • process document
2017/07/26 Shipan Ren 9:00 20:00 11
  • read papers about memory-augmented nmt
2017/07/26 Jiayu Guo 10:00 24:00 14
  • process document
2017/07/27 Shipan Ren 9:00 20:00 11
  • read papers about memory-augmented nmt
2017/07/27 Jiayu Guo 10:00 24:00 14
  • process document
2017/07/28 Shipan Ren 9:00 20:00 11
  • read memory-augmented nmt code
2017/07/28 Jiayu Guo 9:00 24:00 15
  • process document
2017/07/31 Shipan Ren 9:00 20:00 11
  • read memory-augmented nmt code
2017/07/31 Jiayu Guo 10:00 23:00 13
  • split ancient language text to single word
2017/08/1 Shipan Ren 9:00 20:00 11
  • tested these checkpoints of en-fr dataset
  • found the new version takes less time
  • found these two versions have similar complexity and bleu values
2017/08/1 Jiayu Guo 10:00 23:00 13
  • run seq2seq_model
2017/08/2 Shipan Ren 9:00 20:00 11
  • looked for the performance(the bleu value) of other models
  • datasets:WMT2014 en-de and en-fr
2017/08/2 Jiayu Guo 10:00 23:00 13
  • process document
2017/08/3 Shipan Ren 9:00 20:00 11
  • looked for the performance(the bleu value) of other seq2seq models
  • datasets:WMT2014 en-de and en-fr
2017/08/3 Jiayu Guo 10:00 23:00 13
  • process document
2017/08/4 Shipan Ren 9:00 20:00 11
  • learn moses
2017/08/4 Jiayu Guo 10:00 23:00 13
  • search new data(Songshu)
2017/08/7 Shipan Ren 9:00 20:00 11
  • installed and built Moses on the server
2017/08/7 Jiayu Guo 9:00 22:00 13
  • process document
2017/08/8 Shipan Ren 9:00 20:00 11
  • train statistical machine translation model and test it
  • dataset:zh-en small
  • test if moses can work normally
2017/08/8 Jiayu Guo 10:00 21:00 11
  • read tensorflow
2017/08/9 Shipan Ren 9:00 20:00 11
  • code automation scripts to process data,train model and test model
  • toolkit: Moses
2017/08/9 Jiayu Guo 10:00 23:00 13
  • run model with the data of which ancient content was split by single character.
2017/08/10 Shipan Ren 9:00 20:00 11
  • train statistical machine translation models and test it
  • dataset:zh-en big,WMT2014 en-de,WMT2014 en-fr
2017/08/10 Jiayu Guo 9:00 23:00 13
  • process data of Songshu
  • read papers of CNN
2017/08/11 Shipan Ren 9:00 20:00 11
  • collate experimental results
  • compare our baseline model with Moses
2017/08/11 Jiayu Guo 9:00 20:00 11
  • test results.
2017/08/14 Shipan Ren 9:00 20:00 11
  • read paper about THUMT
2017/08/14 Jiayu Guo 10:00 23:00 13
  • learn about Graphic Model of LSTM-Projected BPTT
  • search for data available for translation (Twenty-four-Shi)
2017/08/15 Shipan Ren 9:00 20:00 11
  • read THUMT manual and learn how to use it
2017/08/15 Jiayu Guo 11:00 23:30 12
  • run model with data including Shiji、Zizhitongjian.
2017/08/16 Shipan Ren 9:00 20:00 11
  • train translation models and test them
  • toolkit: THUMT
  • dataset:zh-en small
  • test if THUMT can work normally
2017/08/16 Jiayu Guo 10:00 23:00 10

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。
  • 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.
2017/08/17 Shipan Ren 9:00 20:00 11
  • code automation scripts to process data,train model and test model
  • train translation models and test them
  • toolkit: THUMT
  • dataset:zh-en big
2017/08/17 Jiayu Guo 13:00 23:00 10
  • read source code.
2017/08/18 Shipan Ren 9:00 20:00 11
  • test translation models by using single reference and multiple reference
  • organize all the experimental results(our baseline system,Moses,THUMT)
2017/08/18 Jiayu Guo 13:00 22:00 9
  • read source code.
2017/08/21 Shipan Ren 10:00 22:00 12
  • read the released information of other translation systems
2017/08/21 Jiayu Guo 9:30 21:30 12
  • read the source code and learn tensorflow
2017/08/22 Shipan Ren 10:00 22:00 12
  • cleaned up the code
2017/08/22 Jiayu Guo 9:00 22:00 12
  • read the source code
2017/08/23 Shipan Ren 10:00 21:00 11
  • wrote the documents
2017/08/23 Jiayu Guo 9:00 22:00 11
  • read the source code and learn tensorflow
2017/08/24 Shipan Ren 10:00 20:00 10
  • wrote the documents
2017/08/24 Jiayu Guo 9:10 22:00 10.5
  • read the source code and learn tensorflow
2017/08/25 Shipan Ren 10:00 20:00 10
  • check experimental results
2017/08/25 Jiayu Guo 8:50 22:00 10.5
  • read the source code and learn tensorflow
2017/08/28 Shipan Ren 10:00 20:00 10
  • wrote the paper of ViVi_NMT(version 1.0)
2017/08/28 Jiayu Guo 8:10 21:00 11
  • read the source code and learn tensorflow
2017/08/29 Shipan Ren 10:00 20:00 10
  • wrote the paper of ViVi_NMT(version 1.0)
2017/08/29 Jiayu Guo 11:00 21:00 10
  • read the source code and learn tensorflow
2017/08/30 Shipan Ren 10:00 20:00 10
  • wrote the paper of ViVi_NMT(version 1.0)
2017/08/30 Jiayu Guo 11:30 21:00 9
  • learn VV model
2017/08/31 Shipan Ren 10:00 20:00 10
  • wrote the paper of ViVi_NMT(version 1.0)
2017/08/31 Jiayu Guo 10:00 20:00 10
  • clean up the code
Date Yang Feng Jiyuan Zhang

Past progress

nlp-progress 2017/03

nlp-progress 2017/02

nlp-progress 2017/01

nlp-progress 2016/12

nlp-progress 2016/11

nlp-progress 2016/10

nlp-progress 2016/09

nlp-progress 2016/08

nlp-progress 2016/05-07

nlp-progress 2016/04

取自“http://index.cslt.org/mediawiki/index.php?title=Schedule&oldid=28595”