“Schedule”版本间的差异

来自cslt Wiki
跳转至： 导航、 搜索
（→‎Month Summary）
（→‎Daily Report）
 
（12位用户的377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）
+
* Shiyue Zhang (张诗悦)
−
* Aiting Liu (刘艾婷)
+
* Li Gu (古丽)
−
* Shiyao Li （李诗瑶）
+
* Peilun Xiao (肖培伦)
 +
* Shipan Ren (任师攀)
 +
* Jiayu Guo (郭佳雨)
  
 
===Former Members===
 
===Former Members===
第22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30行： 第33行：
 
! Date !! Person  !! start!! leave !! hours ||status
 
! Date !! Person  !! start!! leave !! hours ||status
 
|-
 
|-
−
| rowspan="4"|2016/08/16 
+
| rowspan="2"|2017/04/02
−
|Ziwei Bai|| 9:30 || 17:30 || 7 ||learn kernel construction,write the first construction method.
+
|Andy Zhang||9:30 ||18:30 ||8 ||  
 +
*preparing EMNLP
 
|-
 
|-
−
|Andy Zhang||9:30  || 17:30  || 7 || prepare for the ML book, watch Wang's video of neural network
+
|Peilun Xiao || || || ||
 
|-
 
|-
−
|Aiting Liu|| 9:30 || 17:30 || 7 || learn Wang's instructional video of Neural Network
+
| rowspan="2"|2017/04/03
 +
|Andy Zhang||9:30 ||18:30 ||8 ||  
 +
*preparing EMNLP
 
|-
 
|-
−
|Shiyao Li ||   ||   || ||
+
|Peilun Xiao || || || ||
 
|-
 
|-
−
| rowspan="4"|2016/08/17
+
| rowspan="2"|2017/04/04
−
|Ziwei Bai|| 9:00 || 18:00  || 8 || rewrite 'the property of Gram matrix' and write the second kernel construction method
+
|Andy Zhang||9:30 ||18:30 ||8 ||  
 +
*preparing EMNLP
 
|-
 
|-
−
|Andy Zhang|| 9:00 || 18:00  || 8 || read materials about Radio basis function networks as well as self-organizing map
+
|Peilun Xiao || || || ||
 
|-
 
|-
−
|Aiting Liu|| 9:00 || 18:00  || 8 || view the information related to the Hopfield network and Boltzmann machine
+
| rowspan="2"|2017/04/05
 +
|Andy Zhang||9:30 ||18:30 ||8 ||  
 +
*preparing EMNLP
 
|-
 
|-
−
|Shiyao Li ||   || ||   ||
+
|Peilun Xiao || || || ||
 
|-
 
|-
−
| rowspan="4"|2016/08/18
+
| rowspan="2"|2017/04/06
−
|Ziwei Bai|| 9:30 ||18:30 || 8 ||learn the 'propert of kernel function'&learn chaos' chatting model predict program
+
|Andy Zhang||9:30 ||18:30 ||8 ||  
 +
*preparing EMNLP
 
|-
 
|-
−
|Andy Zhang||9:30  || 18:30 || 8  || continue preparing for the MLbook
+
|Peilun Xiao || || || ||
 
|-
 
|-
−
|Aiting Liu||9:30   || 18:30 || 8 || prepare for the presentation, learn RBF
+
| rowspan="2"|2017/04/07
 +
|Andy Zhang||9:30 ||18:30 ||8 ||  
 +
*preparing EMNLP
 
|-
 
|-
−
|Shiyao Li ||   ||   || ||
+
|Peilun Xiao || || || ||
 
|-
 
|-
−
| rowspan="4"|2016/08/19
+
| rowspan="2"|2017/04/08
−
|Ziwei Bai|| 9:00  || 18:00  || 8 || finish the first edition of my work of ML book
+
|Andy Zhang||9:30 ||18:30 ||8 ||  
 +
*preparing EMNLP
 
|-
 
|-
−
|Andy Zhang|| 9:00  || 18:00  || 8 ||learn Hopfield network, prepare for the writing
+
|Peilun Xiao || || || ||
 
|-
 
|-
−
|Aiting Liu|| 9:00 || 18:00  || 8 || learn Andrew Ng's online course
+
| rowspan="2"|2017/04/09
 +
|Andy Zhang||9:30 ||18:30 ||8 ||  
 +
*preparing EMNLP
 
|-
 
|-
−
|Shiyao Li ||   ||   || ||
+
|Peilun Xiao || || || ||
 
|-
 
|-
−
| rowspan="4"|2016/08/20
+
| rowspan="2"|2017/04/10
−
|Ziwei Bai|| 9:40  || 18:50  || 8 || perfect my work of the book
+
|Andy Zhang||9:30 ||18:30 ||8 ||  
 +
*preparing EMNLP
 
|-
 
|-
−
|Andy Zhang||   ||   || ||
+
|Peilun Xiao || || || ||
 
|-
 
|-
−
|Aiting Liu||   ||   || ||
+
| rowspan="2"|2017/04/11
 +
|Andy Zhang||9:30 ||18:30 ||8 ||
 +
*preparing EMNLP
 
|-
 
|-
−
|Shiyao Li ||   ||   || ||
+
|Peilun Xiao || || || ||
 
|-
 
|-
−
| rowspan="4"|2016/08/22
+
| rowspan="2"|2017/04/12
−
|Ziwei Bai|| 9:15  || 18:15 ||8 || test Chatting model ,retrain word vector
+
|Andy Zhang||9:30 ||18:30 ||8 ||  
 +
*preparing EMNLP
 
|-
 
|-
−
|Andy Zhang|| 9:15  || 18:15  || 8 || start writing chapter 3, version 0.0.
+
|Peilun Xiao || || || ||
 
|-
 
|-
−
|Aiting Liu||   ||   || ||
+
| rowspan="2"|2017/04/13
 +
|Andy Zhang||9:30 ||18:30 ||8 ||
 +
*preparing EMNLP
 
|-
 
|-
−
|Shiyao Li ||   ||   || ||
+
|Peilun Xiao || || || ||
 
|-
 
|-
−
| rowspan="4"|2016/08/23
+
| rowspan="2"|2017/04/14
−
|Ziwei Bai|| 9:00 || 18:15||8 || 1、retrain NRM model & word vec 2.review paper‘NRM for STC’
+
|Andy Zhang||9:30 ||18:30 ||8 ||  
 +
*preparing EMNLP
 
|-
 
|-
−
|Andy Zhang||9:00 || 18:15 || 8 || continue writing the ML book. mainly worked on MLP today
+
|Peilun Xiao || || || ||
 
|-
 
|-
−
|Aiting Liu||   ||   || ||
+
| rowspan="2"|2017/04/15
 +
|Andy Zhang||9:00 ||15:00 ||6 ||
 +
*preparing EMNLP
 
|-
 
|-
−
|Shiyao Li || 9:00  || 18:15 || 8 || read the book Deep Learning and prepare the presentation of Probability Theory
+
|Peilun Xiao || || || ||
 
|-
 
|-
−
| rowspan="4"|2016/08/24
+
| rowspan="1"|2017/04/18
−
|Ziwei Bai|| 9:05 || 18:05 || 8 || test Chatting model 0-8,modify ASR Python Server Functional Specification
+
|Aodong Li||11:00 ||20:00 ||8 ||  
 +
*Pick up new task in news generation and do literature review
 
|-
 
|-
−
|Andy Zhang|| 9:05|| 18:05 ||8 || mainly wrote the section of MLP & RBF
+
| rowspan="1"|2017/04/19
 +
|Aodong Li||11:00 ||20:00 ||8 ||  
 +
*Literature review
 
|-
 
|-
−
|Aiting Liu||   ||   || ||
+
| rowspan="1"|2017/04/20
 +
|Aodong Li||12:00 ||20:00 ||8 ||
 +
*Literature review
 
|-
 
|-
−
|Shiyao Li || 9:05  || 18:05 || 8 || finish the preparation of the presentation about Linear Algebra and Probability Theory
+
| rowspan="1"|2017/04/21
 +
|Aodong Li||12:00 ||20:00 ||8 ||  
 +
*Literature review
 
|-
 
|-
−
| rowspan="4"|2016/08/25
+
| rowspan="1"|2017/04/24
−
|Ziwei Bai|| 9:20  || 21:00 || 7.5 || 1、test Chatting Model 9-14，and upload to cvss。2、learn  Bengio‘s dialogue system by hierarchical NN（except experiment and result）。
+
|Aodong Li||11:00 ||20:00 ||8 ||  
 +
*Adjust literature review focus
 
|-
 
|-
−
|Andy Zhang|| 9:20  || 21:00 || 7.5 || continue writing chapter3
+
| rowspan="1"|2017/04/25
 +
|Aodong Li||11:00 ||20:00 ||8 ||  
 +
*Literature review
 
|-
 
|-
−
|Aiting Liu||   ||   || ||
+
| rowspan="1"|2017/04/26
 +
|Aodong Li||11:00 ||20:00 ||8 ||
 +
*Literature review
 
|-
 
|-
−
|Shiyao Li || 9:20  || 21:00 || 7.5 || revise the PPT and start to learn tensorflow
+
| rowspan="1"|2017/04/27
 +
|Aodong Li||11:00 ||20:00 ||8 ||  
 +
*Try to reproduce sc-lstm work
 
|-
 
|-
−
| rowspan="4"|2016/08/26
+
| rowspan="1"|2017/04/28
−
|Ziwei Bai|| 9:30  || 18:30 || 8 || prepare for seminar,select 100  posts Suitable for dialogue from weibo data
+
|Aodong Li||11:00 ||20:00 ||8 ||  
 +
*Transfer to new task in machine translation and do literature review
 
|-
 
|-
−
|Andy Zhang|| 9:30  || 18:30  || 8 || continue writing chapter3
+
| rowspan="1"|2017/04/30
 +
|Aodong Li||11:00 ||20:00 ||8 ||  
 +
*Literature review
 
|-
 
|-
−
|Aiting Liu||   ||   || ||
+
| rowspan="1"|2017/05/01
 +
|Aodong Li||11:00 ||20:00 ||8 ||
 +
*Literature review
 
|-
 
|-
−
|Shiyao Li || 9:30  || 18:30 || 8 || self-study tensorflow
+
| rowspan="1"|2017/05/02
 +
|Aodong Li||11:00 ||20:00 ||8 ||  
 +
*Literature review and code review
 
|-
 
|-
−
| rowspan="4"|2016/08/27
+
| rowspan="1"|2017/05/06
−
|Ziwei Bai|| 9:30 || 20:30  || 10 || 1、filter the movie scipts data based on weibo data word vector (30W+pairs) and try to train Chatting Model with the dataset  on the basis of model 31, but load model failed(maybe because the version of tensor flow not consistent).2、find the response Corresponding to the post selected yesterday and test the model (0-34) with it
+
|Aodong Li||14:20 ||17:20||3 ||  
 +
*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
 
|-
 
|-
−
|Aiting Liu||   ||   || ||
+
| rowspan="1"|2017/05/08
 +
|Aodong Li||11:30 ||21:00 ||8 ||
 +
*Code review and version discrepancy solved
 
|-
 
|-
−
|Shiyao 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
 
|-
 
|-
−
| rowspan="4"|2016/08/29
+
| rowspan="1"|2017/05/10
−
|Ziwei Bai|| 9:20 || 18:00   || 7+ || test the Chatting model,count the number of startswith <END> sentences,and natural sentences.
+
|Shipan Ren || 9:00 || 20:00 || 11 ||  
 +
*Entry procedures
 +
*Machine Translation paper reading
 
|-
 
|-
−
|Andy Zhang|| 9:20  || 17:40  || 7+ || continued working on chapter 3, did some revise work & tried to find ways to draw figures
+
| rowspan="1"|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
 
|-
 
|-
−
|Aiting Liu|| 9:20 || 18:20  || 8 || prepare diagrams in the book
+
| rowspan="1"|2017/05/11
 +
|Shipan Ren || 10:00 || 19:30 || 9.5 ||  
 +
*Configure environment
 +
*Run tf_translate code
 +
*Read Machine Translation paper
 
|-
 
|-
−
|Shiyao Li|| 9:20 || 18:20 || 8 || learn the CNN to solve MNIST using tensorflow
+
| 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|| 10:30 || 16:30  || 5 || Read shared paper at the week before the last week
+
| rowspan="1"|2017/05/12
 +
|Aodong Li||13:00 ||21:00 ||8 ||  
 +
*Code double decoding model and read multilingual MT paper
 
|-
 
|-
−
| rowspan="4"|2016/08/30
+
| rowspan="1"|2017/05/13
−
|Ziwei Bai|| 9:15 ||   || ||  
+
|Shipan Ren || 10:00 || 19:00 || 9 ||  
 +
*read machine translation paper
 +
*learne lstm model and seq2seq model
 
|-
 
|-
−
|Andy Zhang||   ||   || ||
+
| rowspan="1"|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'''
 
|-
 
|-
−
|Aiting Liu||   ||   || ||
+
| 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
 
|-
 
|-
−
|Shiyao Li|| 9:15 ||  ||  ||
+
| rowspan="2"|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
 +
|-
 +
| rowspan="2"|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
 +
|-
 +
| 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.
 +
|-
 +
| rowspan="1"|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
 +
|-
 +
| 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
 +
|-
 +
| 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="1"|2017/05/24
 +
|Aodong Li || 13:00 || 21:30 || 8 ||  
 +
*code double-attention one-decoder model
 +
*code double-decoder model
 
|-
 
|-
−
|}
 
  
−
===Month Summary===
+
| rowspan="1"|2017/05/24
 +
|Shipan Ren || 10:00 || 20:00 || 10 ||
 +
*read neural machine translation paper
 +
*read tf_translate code
 +
|-
  
−
{| class="wikitable"
+
| rowspan="2"|2017/05/25
−
!People!! Summary
+
|Shipan Ren || 9:30 || 18:30 || 9 ||
 +
*write document of tf_translate project
 +
*read neural machine translation paper
 +
*read tf_translate code
 
|-
 
|-
−
|Yang Feng ||  
+
|Aodong Li || 13:00 || 22:00 || 9 ||  
−
*surveyed the line works of neural parsing, neural Turing machine and variants of RBMs and fixed the research topic to jointly parsing and understanding with Turing machine
+
* code and debug double attention model
−
*learned tensorflow
+
−
*produced two versions of results of query paraphrase
+
 
|-
 
|-
−
|Jiyuan Zhang ||  
+
 
 +
| rowspan="1"|2017/05/27
 +
|Shipan Ren || 9:30 || 18:30 || 9 ||
 +
*read tf_translate code
 +
*write document of tf_translate project
 
|-
 
|-
−
|Aodong Li ||  
+
| rowspan="1"|2017/05/28
−
*Code:  
+
|Aodong Li || 15:00 || 22:00 || 7 ||  
−
   1. sequence-to-sequence model with attention mechanism for chatting model and lyrics generation in theano and tensorflow
+
*details about experiment:  
−
   2. Rare word embedding on word2vec and the related in C
+
   hidden_size = 500
−
   3. Help Lantian for ICASSP
+
  emb_size = 310
−
*Paper sharing: two shared papers, one for rare word embedding, one for bilingual word embedding
+
  learning_rate = 0.001
−
*ML book: first version of chapter 2, linear model
+
  small data,
−
*Read several papers about RNN, language model, word2vec, sequence-to-sequence model
+
  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'''
 
|-
 
|-
−
|Ziwei Bai ||  
+
| rowspan="1"|2017/05/30
−
*finish part of chapter 5 kernel method
+
|Aodong Li || 15:00 || 21:00 || 6 ||  
−
*retrain & test Chatting Model
+
*details about experiment 1:
−
*share 'the use of tensorflow'
+
  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
 
|-
 
|-
−
|Andy Zhang ||  
+
| rowspan="2"|2017/05/31
−
*shared the principle of word2vec
+
|Shipan Ren || 10:00 || 19:30 || 9.5 ||  
−
*read several papers about comparison of sentence similarity
+
*run and test tf_translate code
−
*wrote chapter 3 neural network of the ML book
+
*write document of tf_translate project
 
|-
 
|-
−
|Aiting Liu ||  
+
|Aodong Li || 12:00 || 20:30 || 8.5 ||  
−
*share two papers:
+
* details about experiment 1:  
−
1.Intrinsic Subspace Evaluation of Word Embedding Representations    [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/6/68/Intrinsic_Subspace_Evaluation_of_Word_Embedding_Representations.pdf pdf]]
+
  '''final_attn = 4/3attn_1 + 2/3attn_2'''
−
[[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/1/17/Intrinsic_Subspace_Evaluation_of_Word_Embedding_Representations.pptx slides]]
+
  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.
 +
|-
 +
| 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="1"|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
 +
|-
 +
| 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
 +
|-
 +
| rowspan="1"|2017/06/05
 +
|Aodong Li || 10:00 || 19:00 || 8 ||
 +
* Prepare for APSIPA paper
 +
|-
 +
| rowspan="1"|2017/06/06
 +
|Aodong Li || 10:00 || 19:00 || 8 ||
 +
* Prepare for APSIPA paper
 +
|-
 +
| rowspan="1"|2017/06/07
 +
|Aodong Li || 10:00 || 19:00 || 8 ||
 +
* Prepare for APSIPA paper
 +
|-
 +
| rowspan="1"|2017/06/08
 +
|Aodong Li || 10:00 || 19:00 || 8 ||
 +
* Prepare for APSIPA paper
 +
|-
 +
| rowspan="1"|2017/06/09
 +
|Aodong Li || 10:00 || 19:00 || 8 ||
 +
* Prepare for APSIPA paper
 +
|-
 +
| rowspan="1"|2017/06/12
 +
|Aodong Li || 10:00 || 19:00 || 8 ||
 +
* Prepare for APSIPA paper
 +
|-
 +
| rowspan="1"|2017/06/13
 +
|Aodong Li || 10:00 || 19:00 || 8 ||
 +
* Prepare for APSIPA paper
 +
|-
 +
| rowspan="1"|2017/06/14
 +
|Aodong Li || 10:00 || 19:00 || 8 ||
 +
* Prepare for APSIPA paper
 +
|-
 +
| rowspan="1"|2017/06/15
 +
|Aodong Li || 10:00 || 19:00 || 8 ||
 +
* Prepare for APSIPA paper
 +
* Read paper about MT involving grammar
 +
|-
 +
| rowspan="1"|2017/06/16
 +
|Aodong Li || 10:00 || 19:00 || 8 ||
 +
* Prepare for APSIPA paper
 +
* Read paper about MT involving grammar
 +
|-
 +
| rowspan="1"|2017/06/19
 +
|Aodong Li || 10:00 || 19:00 || 8 ||
 +
* Completed APSIPA paper
 +
* Took new task in style translation
 +
|-
 +
| rowspan="1"|2017/06/20
 +
|Aodong Li || 10:00 || 19:00 || 8 ||
 +
* Tried synonyms substitution
 +
|-
 +
| rowspan="1"|2017/06/21
 +
|Aodong Li || 10:00 || 19:00 || 8 ||
 +
* Tried post edit like synonyms substitution but this didn't work
 +
|-
 +
| rowspan="1"|2017/06/22
 +
|Aodong Li || 10:00 || 19:00 || 8 ||
 +
* Trained a GRU language model to determine similar word
 +
|-
 +
| rowspan="2"|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
 +
|-
 +
| 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
 +
|-
 +
|Aodong Li || 10:00 || 19:00 || 8 ||
 +
* Tried to figure out new ways to change the text style
 +
|-
 +
| rowspan="2"|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
 +
|-
 +
| rowspan="2"|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
 +
|-
 +
| 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)
 +
|-
 +
|Aodong Li || 10:00 || 19:00 || 8 ||
 +
* Read style transfer papers
 +
|-
 +
| 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
 +
|-
 +
|Aodong Li || 10:00 || 19:00 || 8 ||
 +
* Read style transfer papers
 +
|-
 +
| 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
  
−
2.A Sentence Interaction Network for Modeling Dependence between Sentences
 
−
[[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/0/04/A_Sentence_Interaction_Network_for_Modeling_Dependence_between_Sentences.pdf pdf]]
 
−
[[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/6/6c/A_Sentence_Interaction_Network_for_Modeling_Dependence_between_Sentences.pptx slides]]
 
−
*write chapter2 linear model
 
−
*help Andy complete chapter3 neural network
 
 
|-
 
|-
−
|Shiyao Li ||  
+
| rowspan="1"|2017/07/04
−
*prepare the data for question-pair task.
+
|Shipan Ren || 9:00 || 21:00 || 12 ||  
−
*use SRILM to train the language model and Moses to train the task
+
* recorded experimental results
−
*share a paper about LSTM and do a presentation.
+
* 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
  
−
===Time Off Table===
+
|-
 +
| rowspan="1"|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
  
−
{| class="wikitable"
 
−
! Date !! Yang Feng !! Jiyuan Zhang !! Aodong Li !! Ziwei Bai !! Andy Zhang !! Aiitng Liu !! Shiyao Li
 
 
|-
 
|-
−
|2016/8/15 || || || || || || || 8 hours
+
| 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
 
|-
 
|-
−
|2016/8/16 || || || || || || || 8 hours
+
| 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
 
|-
 
|-
−
|2016/8/17 || || || || || || || 8 hours
+
| 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
 +
 
 
|-
 
|-
−
|2016/8/18 || 2 hours || || || || || || 4 hours
+
| 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
 
|-
 
|-
−
|2016/8/19 || || 6 hours || || || || || 8 hours
+
| rowspan="1"|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)
 +
 
 
|-
 
|-
−
|2016/8/22 || || || || || || 8 hours || 8 hours
+
| 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
 +
 
 
|-
 
|-
−
|2016/8/23 || || 2 hours || || || || 8 hours ||
+
| rowspan="1"|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
 +
 
 
|-
 
|-
−
|2016/8/24 || || || || || || 8 hours ||
+
| 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
 +
 
 
|-
 
|-
−
|2016/8/25 || || || || || || 8 hours ||
+
| rowspan="1"|2017/07/17
 +
|Shipan Ren || 9:00 || 20:00 || 11 ||  
 +
* downloaded the wmt2014 data sets and processed it
 +
 
 
|-
 
|-
−
|2016/8/26 || || || 5 hours || || || 8 hours ||
+
| rowspan="1"|2017/07/18
 +
|Shipan Ren || 9:00 || 20:00 || 11 ||
 +
* processed data
 +
 
 +
|-
 +
| rowspan="1"|2017/07/18
 +
|Jiayu Guo || 8:30|| 22:00 || 14 ||
 +
* read model code.
 +
 
 +
|-
 +
| rowspan="1"|2017/07/19
 +
|Shipan Ren || 9:00 || 20:00 || 11 ||
 +
* processed data
 +
|-
 +
| rowspan="1"|2017/07/19
 +
|Jiayu Guo || 9:00|| 22:00 || 13 ||
 +
* read papers of bleu.
 +
|-
 +
| rowspan="1"|2017/07/20
 +
|Shipan Ren || 9:00 || 20:00 || 11 ||
 +
* processed data
 +
|-
 +
| rowspan="1"|2017/07/20
 +
|Jiayu Guo || 9:00|| 22:00 || 13 ||
 +
* read papers of attention mechanism.
 +
|-
 +
| 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
 +
|-
 +
| rowspan="1"|2017/07/21
 +
|Jiayu Guo || 10:00|| 23:00 || 13 ||
 +
* process document
 +
 
 +
|-
 +
| 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
 +
 
 +
|-
 +
| 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
 +
 
 +
|-
 +
| rowspan="1"|2017/07/26
 +
|Shipan Ren || 9:00 || 20:00 || 11 ||
 +
* read papers about memory-augmented nmt
 +
 
 +
|-
 +
| rowspan="1"|2017/07/26
 +
|Jiayu Guo || 10:00|| 24:00 || 14 ||
 +
* process document
 +
 
 +
|-
 +
| rowspan="1"|2017/07/27
 +
|Shipan Ren || 9:00 || 20:00 || 11 ||
 +
* read papers about memory-augmented nmt
 +
 
 +
|-
 +
| rowspan="1"|2017/07/27
 +
|Jiayu Guo || 10:00|| 24:00 || 14 ||
 +
* process document
 +
 
 +
|-
 +
| rowspan="1"|2017/07/28
 +
|Shipan Ren || 9:00 || 20:00 || 11 ||
 +
* read memory-augmented nmt code
 +
 
 +
|-
 +
| rowspan="1"|2017/07/28
 +
|Jiayu Guo || 9:00|| 24:00 || 15 ||
 +
* process document
 +
|
 +
 
 +
|-
 +
| rowspan="1"|2017/07/31
 +
|Shipan Ren || 9:00 || 20:00 || 11 ||
 +
* read memory-augmented nmt code
 +
|-
 +
| 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===
 +
 
 +
{| class="wikitable"
 +
! Date !! Yang Feng !! Jiyuan Zhang
 
|-
 
|-
−
|2016/8/29 || || || 0.5 hours || || || ||
 
 
|}
 
|}
  
 
==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 2016/08]]
 
[[nlp-progress 2016/08]]
  

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