“Schedule”版本间的差异
来自cslt Wiki
(→Work Progress) |
(→Daily Report) |
||
(8位用户的152个中间修订版本未显示) | |||
第12行: | 第12行: | ||
* Li Gu (古丽) | * Li Gu (古丽) | ||
* Peilun Xiao (肖培伦) | * Peilun Xiao (肖培伦) | ||
+ | * Shipan Ren (任师攀) | ||
+ | * Jiayu Guo (郭佳雨) | ||
===Former Members=== | ===Former Members=== | ||
第31行: | 第33行: | ||
! Date !! Person !! start!! leave !! hours ||status | ! Date !! Person !! start!! leave !! hours ||status | ||
|- | |- | ||
− | | rowspan=" | + | | rowspan="2"|2017/04/02 |
− | |Andy Zhang|| 9:30||18:30 ||8 || | + | |Andy Zhang||9:30 ||18:30 ||8 || |
− | * | + | *preparing EMNLP |
− | + | ||
|- | |- | ||
− | | | + | |Peilun Xiao || || || || |
− | + | ||
|- | |- | ||
− | + | | rowspan="2"|2017/04/03 | |
− | + | |Andy Zhang||9:30 ||18:30 ||8 || | |
− | + | *preparing EMNLP | |
− | + | ||
− | | rowspan=" | + | |
− | |Andy Zhang|| 9:30|| 18:30|| 8|| | + | |
− | * | + | |
− | + | ||
|- | |- | ||
− | | | + | |Peilun Xiao || || || || |
|- | |- | ||
− | | | + | | rowspan="2"|2017/04/04 |
− | + | |Andy Zhang||9:30 ||18:30 ||8 || | |
− | + | *preparing EMNLP | |
− | | | + | |
− | | | + | |
− | * | + | |
|- | |- | ||
− | | | + | |Peilun Xiao || || || || |
− | | | + | |
− | + | ||
− | + | ||
|- | |- | ||
− | | | + | | rowspan="2"|2017/04/05 |
− | * | + | |Andy Zhang||9:30 ||18:30 ||8 || |
− | + | *preparing EMNLP | |
|- | |- | ||
− | + | |Peilun Xiao || || || || | |
− | + | ||
− | + | ||
− | + | ||
− | |Peilun Xiao || | + | |
− | + | ||
|- | |- | ||
− | | rowspan=" | + | | rowspan="2"|2017/04/06 |
− | |Andy Zhang|| 9:30 || | + | |Andy Zhang||9:30 ||18:30 ||8 || |
− | * | + | *preparing EMNLP |
− | + | ||
|- | |- | ||
− | | | + | |Peilun Xiao || || || || |
|- | |- | ||
− | | | + | | rowspan="2"|2017/04/07 |
− | + | |Andy Zhang||9:30 ||18:30 ||8 || | |
− | + | *preparing EMNLP | |
− | | | + | |
− | + | ||
− | * | + | |
− | + | ||
|- | |- | ||
− | | | + | |Peilun Xiao || || || || |
− | | | + | |
− | + | ||
− | + | ||
|- | |- | ||
− | | | + | | rowspan="2"|2017/04/08 |
− | * | + | |Andy Zhang||9:30 ||18:30 ||8 || |
− | + | *preparing EMNLP | |
|- | |- | ||
− | |||
− | |||
− | |||
− | |||
|Peilun Xiao || || || || | |Peilun Xiao || || || || | ||
|- | |- | ||
− | | rowspan=" | + | | rowspan="2"|2017/04/09 |
− | |Andy Zhang|| 9:30 || | + | |Andy Zhang||9:30 ||18:30 ||8 || |
− | * | + | *preparing EMNLP |
− | + | ||
|- | |- | ||
− | | | + | |Peilun Xiao || || || || |
− | + | ||
− | + | ||
− | + | ||
|- | |- | ||
− | | | + | | rowspan="2"|2017/04/10 |
− | + | |Andy Zhang||9:30 ||18:30 ||8 || | |
− | + | *preparing EMNLP | |
− | + | ||
− | | | + | |
− | * | + | |
|- | |- | ||
− | | | + | |Peilun Xiao || || || || |
− | | | + | |
− | + | ||
− | + | ||
|- | |- | ||
− | | | + | | rowspan="2"|2017/04/11 |
− | * | + | |Andy Zhang||9:30 ||18:30 ||8 || |
− | + | *preparing EMNLP | |
− | + | ||
|- | |- | ||
− | |||
− | |||
− | |||
|Peilun Xiao || || || || | |Peilun Xiao || || || || | ||
|- | |- | ||
− | | rowspan=" | + | | rowspan="2"|2017/04/12 |
− | |Andy Zhang|| | + | |Andy Zhang||9:30 ||18:30 ||8 || |
+ | *preparing EMNLP | ||
|- | |- | ||
− | | | + | |Peilun Xiao || || || || |
+ | |- | ||
+ | | rowspan="2"|2017/04/13 | ||
+ | |Andy Zhang||9:30 ||18:30 ||8 || | ||
+ | *preparing EMNLP | ||
|- | |- | ||
− | |||
− | |||
− | |||
|Peilun Xiao || || || || | |Peilun Xiao || || || || | ||
|- | |- | ||
− | | rowspan=" | + | | rowspan="2"|2017/04/14 |
− | |Andy Zhang|| | + | |Andy Zhang||9:30 ||18:30 ||8 || |
+ | *preparing EMNLP | ||
|- | |- | ||
− | | | + | |Peilun Xiao || || || || |
+ | |- | ||
+ | | rowspan="2"|2017/04/15 | ||
+ | |Andy Zhang||9:00 ||15:00 ||6 || | ||
+ | *preparing EMNLP | ||
|- | |- | ||
− | |||
− | |||
− | |||
|Peilun Xiao || || || || | |Peilun Xiao || || || || | ||
|- | |- | ||
− | | rowspan=" | + | | rowspan="1"|2017/04/18 |
− | | | + | |Aodong Li||11:00 ||20:00 ||8 || |
+ | *Pick up new task in news generation and do literature review | ||
|- | |- | ||
− | | | + | | rowspan="1"|2017/04/19 |
+ | |Aodong Li||11:00 ||20:00 ||8 || | ||
+ | *Literature review | ||
|- | |- | ||
− | | | + | | rowspan="1"|2017/04/20 |
− | * | + | |Aodong Li||12:00 ||20:00 ||8 || |
− | + | *Literature review | |
− | + | ||
− | + | ||
|- | |- | ||
− | | rowspan=" | + | | rowspan="1"|2017/04/21 |
− | | | + | |Aodong Li||12:00 ||20:00 ||8 || |
+ | *Literature review | ||
|- | |- | ||
− | | | + | | rowspan="1"|2017/04/24 |
+ | |Aodong Li||11:00 ||20:00 ||8 || | ||
+ | *Adjust literature review focus | ||
|- | |- | ||
− | | | + | | rowspan="1"|2017/04/25 |
− | * | + | |Aodong Li||11:00 ||20:00 ||8 || |
− | + | *Literature review | |
− | + | ||
− | + | ||
|- | |- | ||
− | |} | + | | rowspan="1"|2017/04/26 |
+ | |Aodong Li||11:00 ||20:00 ||8 || | ||
+ | *Literature review | ||
+ | |- | ||
+ | | rowspan="1"|2017/04/27 | ||
+ | |Aodong Li||11:00 ||20:00 ||8 || | ||
+ | *Try to reproduce sc-lstm work | ||
+ | |- | ||
+ | | rowspan="1"|2017/04/28 | ||
+ | |Aodong Li||11:00 ||20:00 ||8 || | ||
+ | *Transfer to new task in machine translation and do literature review | ||
+ | |- | ||
+ | | rowspan="1"|2017/04/30 | ||
+ | |Aodong Li||11:00 ||20:00 ||8 || | ||
+ | *Literature review | ||
+ | |- | ||
+ | | rowspan="1"|2017/05/01 | ||
+ | |Aodong Li||11:00 ||20:00 ||8 || | ||
+ | *Literature review | ||
+ | |- | ||
+ | | rowspan="1"|2017/05/02 | ||
+ | |Aodong Li||11:00 ||20:00 ||8 || | ||
+ | *Literature review and code review | ||
+ | |- | ||
+ | | rowspan="1"|2017/05/06 | ||
+ | |Aodong Li||14:20 ||17:20||3 || | ||
+ | *Code review | ||
+ | |- | ||
+ | | rowspan="1"|2017/05/07 | ||
+ | |Aodong Li||13:30 ||22:00||8 || | ||
+ | *Code review and experiment started, but version discrepancy encountered | ||
+ | |- | ||
+ | | rowspan="1"|2017/05/08 | ||
+ | |Aodong Li||11:30 ||21:00 ||8 || | ||
+ | *Code review and version discrepancy solved | ||
+ | |- | ||
+ | | 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="1"|2017/05/10 | ||
+ | |Shipan Ren || 9:00 || 20:00 || 11 || | ||
+ | *Entry procedures | ||
+ | *Machine Translation paper reading | ||
+ | |- | ||
+ | | 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 | ||
+ | |- | ||
+ | | rowspan="1"|2017/05/11 | ||
+ | |Shipan Ren || 10:00 || 19:30 || 9.5 || | ||
+ | *Configure environment | ||
+ | *Run tf_translate code | ||
+ | *Read Machine Translation paper | ||
+ | |- | ||
+ | | 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 | ||
+ | |- | ||
+ | | rowspan="1"|2017/05/12 | ||
+ | |Aodong Li||13:00 ||21:00 ||8 || | ||
+ | *Code double decoding model and read multilingual MT paper | ||
+ | |- | ||
+ | | rowspan="1"|2017/05/13 | ||
+ | |Shipan Ren || 10:00 || 19:00 || 9 || | ||
+ | *read machine translation paper | ||
+ | *learne lstm model and seq2seq model | ||
+ | |- | ||
+ | | 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''' | ||
+ | |- | ||
+ | | 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 | ||
+ | |- | ||
+ | | 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 | ||
+ | |- | ||
+ | |||
+ | | rowspan="1"|2017/05/24 | ||
+ | |Shipan Ren || 10:00 || 20:00 || 10 || | ||
+ | *read neural machine translation paper | ||
+ | *read tf_translate code | ||
+ | |- | ||
+ | |||
+ | | rowspan="2"|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 | ||
+ | |- | ||
+ | |||
+ | | rowspan="1"|2017/05/27 | ||
+ | |Shipan Ren || 9:30 || 18:30 || 9 || | ||
+ | *read tf_translate code | ||
+ | *write document of tf_translate project | ||
+ | |- | ||
+ | | rowspan="1"|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''' | ||
+ | |- | ||
+ | | 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 | ||
+ | |- | ||
+ | | 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 || 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. | ||
+ | |- | ||
+ | | 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 | ||
+ | |||
+ | |- | ||
+ | | 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="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 | ||
+ | |||
+ | |- | ||
+ | | 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 | ||
+ | |- | ||
+ | | 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 | ||
+ | |- | ||
+ | | 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 | ||
+ | |||
+ | |- | ||
+ | | 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="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) | ||
+ | |||
+ | |- | ||
+ | | 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 | ||
+ | |||
+ | |- | ||
+ | | 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 | ||
+ | |||
+ | |- | ||
+ | | 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 | ||
+ | |||
+ | |- | ||
+ | | rowspan="1"|2017/07/17 | ||
+ | |Shipan Ren || 9:00 || 20:00 || 11 || | ||
+ | * downloaded the wmt2014 data sets and processed it | ||
+ | |||
+ | |- | ||
+ | | 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=== | ===Time Off Table=== | ||
第187行: | 第972行: | ||
==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 2016/11]] |
2017年9月4日 (一) 07:41的最后版本
目录
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
Date | Person | start | leave | hours | status | |
---|---|---|---|---|---|---|
2017/04/02 | Andy Zhang | 9:30 | 18:30 | 8 |
| |
Peilun Xiao | ||||||
2017/04/03 | Andy Zhang | 9:30 | 18:30 | 8 |
| |
Peilun Xiao | ||||||
2017/04/04 | Andy Zhang | 9:30 | 18:30 | 8 |
| |
Peilun Xiao | ||||||
2017/04/05 | Andy Zhang | 9:30 | 18:30 | 8 |
| |
Peilun Xiao | ||||||
2017/04/06 | Andy Zhang | 9:30 | 18:30 | 8 |
| |
Peilun Xiao | ||||||
2017/04/07 | Andy Zhang | 9:30 | 18:30 | 8 |
| |
Peilun Xiao | ||||||
2017/04/08 | Andy Zhang | 9:30 | 18:30 | 8 |
| |
Peilun Xiao | ||||||
2017/04/09 | Andy Zhang | 9:30 | 18:30 | 8 |
| |
Peilun Xiao | ||||||
2017/04/10 | Andy Zhang | 9:30 | 18:30 | 8 |
| |
Peilun Xiao | ||||||
2017/04/11 | Andy Zhang | 9:30 | 18:30 | 8 |
| |
Peilun Xiao | ||||||
2017/04/12 | Andy Zhang | 9:30 | 18:30 | 8 |
| |
Peilun Xiao | ||||||
2017/04/13 | Andy Zhang | 9:30 | 18:30 | 8 |
| |
Peilun Xiao | ||||||
2017/04/14 | Andy Zhang | 9:30 | 18:30 | 8 |
| |
Peilun Xiao | ||||||
2017/04/15 | Andy Zhang | 9:00 | 15:00 | 6 |
| |
Peilun Xiao | ||||||
2017/04/18 | Aodong Li | 11:00 | 20:00 | 8 |
| |
2017/04/19 | Aodong Li | 11:00 | 20:00 | 8 |
| |
2017/04/20 | Aodong Li | 12:00 | 20:00 | 8 |
| |
2017/04/21 | Aodong Li | 12:00 | 20:00 | 8 |
| |
2017/04/24 | Aodong Li | 11:00 | 20:00 | 8 |
| |
2017/04/25 | Aodong Li | 11:00 | 20:00 | 8 |
| |
2017/04/26 | Aodong Li | 11:00 | 20:00 | 8 |
| |
2017/04/27 | Aodong Li | 11:00 | 20:00 | 8 |
| |
2017/04/28 | Aodong Li | 11:00 | 20:00 | 8 |
| |
2017/04/30 | Aodong Li | 11:00 | 20:00 | 8 |
| |
2017/05/01 | Aodong Li | 11:00 | 20:00 | 8 |
| |
2017/05/02 | Aodong Li | 11:00 | 20:00 | 8 |
| |
2017/05/06 | Aodong Li | 14:20 | 17:20 | 3 |
| |
2017/05/07 | Aodong Li | 13:30 | 22:00 | 8 |
| |
2017/05/08 | Aodong Li | 11:30 | 21:00 | 8 |
| |
2017/05/09 | Aodong Li | 13:00 | 22:00 | 9 |
small data, 1st and 2nd translator uses the same training data, 2nd translator uses random initialized embedding
BASELINE: 43.87 best result of our model: 42.56 | |
2017/05/10 | Shipan Ren | 9:00 | 20:00 | 11 |
| |
2017/05/10 | Aodong Li | 13:30 | 22:00 | 8 |
small data, 1st and 2nd translator uses the different training data, counting 22000 and 22017 seperately 2nd translator uses random initialized embedding
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.
| |
2017/05/11 | Shipan Ren | 10:00 | 19:30 | 9.5 |
| |
2017/05/11 | Aodong Li | 13:00 | 21:00 | 8 |
small data, 1st and 2nd translator uses the same training data, 2nd translator uses constant untrainable embedding imported from 1st translator's decoder
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.
| |
2017/05/12 | Aodong Li | 13:00 | 21:00 | 8 |
| |
2017/05/13 | Shipan Ren | 10:00 | 19:00 | 9 |
| |
2017/05/14 | Aodong Li | 10:00 | 20:00 | 9 |
small data, 2nd translator uses as training data the concat(Chinese, machine translated English), 2nd translator uses random initialized embedding
BASELINE: 43.87 best result of our model: 43.53
| |
2017/05/15 | Shipan Ren | 9:30 | 19:00 | 9.5 |
| |
2017/05/17 | Shipan Ren | 9:30 | 19:30 | 10 |
| |
Aodong Li | 13:30 | 24:00 | 9 |
| ||
2017/05/18 | Shipan Ren | 10:00 | 19:00 | 9 |
| |
Aodong Li | 12:30 | 21:00 | 8 |
| ||
2017/05/19 | Aodong Li | 12:30 | 20:30 | 8 |
| |
2017/05/21 | Aodong Li | 10:30 | 18:30 | 8 |
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
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
| |
2017/05/22 | Aodong Li | 14:00 | 22:00 | 8 |
| |
2017/05/23 | Aodong Li | 13:00 | 21:30 | 8 |
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
BASELINE: 43.87 best result of our model: 42.19 Overfitting? In overall, the 2nd translator performs worse than baseline
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
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.
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.
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 |
| |
2017/05/24 | Shipan Ren | 10:00 | 20:00 | 10 |
| |
2017/05/25 | Shipan Ren | 9:30 | 18:30 | 9 |
| |
Aodong Li | 13:00 | 22:00 | 9 |
| ||
2017/05/27 | Shipan Ren | 9:30 | 18:30 | 9 |
| |
2017/05/28 | Aodong Li | 15:00 | 22:00 | 7 |
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
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 |
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
BASELINE: 43.87 best result of our model: 42.36
final_attn = 2/3attn_1 + 4/3attn_2 2nd translator uses constant initialized embedding
BASELINE: 43.87 best result of our model: 45.32
final_attn = attn_1 + attn_2 2nd translator uses constant initialized embedding
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 |
| |
Aodong Li | 12:00 | 20:30 | 8.5 |
final_attn = 4/3attn_1 + 2/3attn_2 2nd translator uses constant initialized embedding
BASELINE: 43.87 best result of our model: 45.79
| ||
2017/06/01 | Aodong Li | 13:00 | 24:00 | 11 |
| |
2017/06/02 | Aodong Li | 13:00 | 22:00 | 9 |
| |
2017/06/03 | Aodong Li | 13:00 | 21:00 | 8 |
| |
2017/06/05 | Aodong Li | 10:00 | 19:00 | 8 |
| |
2017/06/06 | Aodong Li | 10:00 | 19:00 | 8 |
| |
2017/06/07 | Aodong Li | 10:00 | 19:00 | 8 |
| |
2017/06/08 | Aodong Li | 10:00 | 19:00 | 8 |
| |
2017/06/09 | Aodong Li | 10:00 | 19:00 | 8 |
| |
2017/06/12 | Aodong Li | 10:00 | 19:00 | 8 |
| |
2017/06/13 | Aodong Li | 10:00 | 19:00 | 8 |
| |
2017/06/14 | Aodong Li | 10:00 | 19:00 | 8 |
| |
2017/06/15 | Aodong Li | 10:00 | 19:00 | 8 |
| |
2017/06/16 | Aodong Li | 10:00 | 19:00 | 8 |
| |
2017/06/19 | Aodong Li | 10:00 | 19:00 | 8 |
| |
2017/06/20 | Aodong Li | 10:00 | 19:00 | 8 |
| |
2017/06/21 | Aodong Li | 10:00 | 19:00 | 8 |
| |
2017/06/22 | Aodong Li | 10:00 | 19:00 | 8 |
| |
2017/06/23 | Shipan Ren | 10:00 | 21:00 | 11 |
| |
Aodong Li | 10:00 | 19:00 | 8 |
| ||
2017/06/26 | Shipan Ren | 10:00 | 21:00 | 11 |
| |
Aodong Li | 10:00 | 19:00 | 8 |
| ||
2017/06/27 | Shipan Ren | 10:00 | 20:00 | 10 |
| |
Aodong Li | 10:00 | 19:00 | 8 |
| ||
2017/06/28 | Shipan Ren | 10:00 | 19:00 | 9 |
| |
Aodong Li | 10:00 | 19:00 | 8 |
| ||
2017/06/29 | Shipan Ren | 10:00 | 20:00 | 10 |
| |
Aodong Li | 10:00 | 19:00 | 8 |
| ||
2017/06/30 | Shipan Ren | 10:00 | 24:00 | 14 |
| |
Aodong Li | 10:00 | 19:00 | 8 |
| ||
2017/07/03 | Shipan Ren | 9:00 | 21:00 | 12 |
| |
2017/07/04 | Shipan Ren | 9:00 | 21:00 | 12 |
| |
2017/07/05 | Shipan Ren | 9:00 | 21:00 | 12 |
| |
2017/07/06 | Shipan Ren | 9:00 | 21:00 | 12 |
| |
2017/07/07 | Shipan Ren | 9:00 | 21:00 | 12 |
| |
2017/07/08 | Shipan Ren | 9:00 | 21:00 | 12 |
| |
2017/07/10 | Shipan Ren | 9:00 | 20:00 | 11 |
| |
2017/07/11 | Shipan Ren | 9:00 | 20:00 | 11 |
| |
2017/07/12 | Shipan Ren | 9:00 | 20:00 | 11 |
| |
2017/07/13 | Shipan Ren | 9:00 | 20:00 | 11 |
reason: improper distribution of resources by the tensorflow0.1 frame leads to exhaustion of memory resources
| |
2017/07/14 | Shipan Ren | 9:00 | 20:00 | 11 |
| |
2017/07/17 | Shipan Ren | 9:00 | 20:00 | 11 |
| |
2017/07/18 | Shipan Ren | 9:00 | 20:00 | 11 |
| |
2017/07/18 | Jiayu Guo | 8:30 | 22:00 | 14 |
| |
2017/07/19 | Shipan Ren | 9:00 | 20:00 | 11 |
| |
2017/07/19 | Jiayu Guo | 9:00 | 22:00 | 13 |
| |
2017/07/20 | Shipan Ren | 9:00 | 20:00 | 11 |
| |
2017/07/20 | Jiayu Guo | 9:00 | 22:00 | 13 |
| |
2017/07/21 | Shipan Ren | 9:00 | 20:00 | 11 |
| |
2017/07/21 | Jiayu Guo | 10:00 | 23:00 | 13 |
| |
2017/07/24 | Shipan Ren | 9:00 | 20:00 | 11 |
| |
2017/07/24 | Jiayu Guo | 9:00 | 22:00 | 13 |
| |
2017/07/25 | Shipan Ren | 9:00 | 20:00 | 11 |
| |
2017/07/25 | Jiayu Guo | 9:00 | 23:00 | 14 |
| |
2017/07/26 | Shipan Ren | 9:00 | 20:00 | 11 |
| |
2017/07/26 | Jiayu Guo | 10:00 | 24:00 | 14 |
| |
2017/07/27 | Shipan Ren | 9:00 | 20:00 | 11 |
| |
2017/07/27 | Jiayu Guo | 10:00 | 24:00 | 14 |
| |
2017/07/28 | Shipan Ren | 9:00 | 20:00 | 11 |
| |
2017/07/28 | Jiayu Guo | 9:00 | 24:00 | 15 |
|
|
2017/07/31 | Shipan Ren | 9:00 | 20:00 | 11 |
| |
2017/07/31 | Jiayu Guo | 10:00 | 23:00 | 13 |
|
|
2017/08/1 | Shipan Ren | 9:00 | 20:00 | 11 |
| |
2017/08/1 | Jiayu Guo | 10:00 | 23:00 | 13 |
|
|
2017/08/2 | Shipan Ren | 9:00 | 20:00 | 11 |
| |
2017/08/2 | Jiayu Guo | 10:00 | 23:00 | 13 |
| |
2017/08/3 | Shipan Ren | 9:00 | 20:00 | 11 |
| |
2017/08/3 | Jiayu Guo | 10:00 | 23:00 | 13 |
| |
2017/08/4 | Shipan Ren | 9:00 | 20:00 | 11 |
| |
2017/08/4 | Jiayu Guo | 10:00 | 23:00 | 13 |
| |
2017/08/7 | Shipan Ren | 9:00 | 20:00 | 11 |
| |
2017/08/7 | Jiayu Guo | 9:00 | 22:00 | 13 |
| |
2017/08/8 | Shipan Ren | 9:00 | 20:00 | 11 |
| |
2017/08/8 | Jiayu Guo | 10:00 | 21:00 | 11 |
| |
2017/08/9 | Shipan Ren | 9:00 | 20:00 | 11 |
| |
2017/08/9 | Jiayu Guo | 10:00 | 23:00 | 13 |
| |
2017/08/10 | Shipan Ren | 9:00 | 20:00 | 11 |
| |
2017/08/10 | Jiayu Guo | 9:00 | 23:00 | 13 |
| |
2017/08/11 | Shipan Ren | 9:00 | 20:00 | 11 |
| |
2017/08/11 | Jiayu Guo | 9:00 | 20:00 | 11 |
| |
2017/08/14 | Shipan Ren | 9:00 | 20:00 | 11 |
| |
2017/08/14 | Jiayu Guo | 10:00 | 23:00 | 13 |
| |
2017/08/15 | Shipan Ren | 9:00 | 20:00 | 11 |
| |
2017/08/15 | Jiayu Guo | 11:00 | 23:30 | 12 |
| |
2017/08/16 | Shipan Ren | 9:00 | 20:00 | 11 |
| |
2017/08/16 | Jiayu Guo | 10:00 | 23:00 | 10 |
checkpoint-100000 translation model BLEU: 11.11
| |
2017/08/17 | Shipan Ren | 9:00 | 20:00 | 11 |
| |
2017/08/17 | Jiayu Guo | 13:00 | 23:00 | 10 |
| |
2017/08/18 | Shipan Ren | 9:00 | 20:00 | 11 |
| |
2017/08/18 | Jiayu Guo | 13:00 | 22:00 | 9 |
| |
2017/08/21 | Shipan Ren | 10:00 | 22:00 | 12 |
| |
2017/08/21 | Jiayu Guo | 9:30 | 21:30 | 12 |
| |
2017/08/22 | Shipan Ren | 10:00 | 22:00 | 12 |
| |
2017/08/22 | Jiayu Guo | 9:00 | 22:00 | 12 |
| |
2017/08/23 | Shipan Ren | 10:00 | 21:00 | 11 |
| |
2017/08/23 | Jiayu Guo | 9:00 | 22:00 | 11 |
| |
2017/08/24 | Shipan Ren | 10:00 | 20:00 | 10 |
| |
2017/08/24 | Jiayu Guo | 9:10 | 22:00 | 10.5 |
| |
2017/08/25 | Shipan Ren | 10:00 | 20:00 | 10 |
| |
2017/08/25 | Jiayu Guo | 8:50 | 22:00 | 10.5 |
| |
2017/08/28 | Shipan Ren | 10:00 | 20:00 | 10 |
| |
2017/08/28 | Jiayu Guo | 8:10 | 21:00 | 11 |
| |
2017/08/29 | Shipan Ren | 10:00 | 20:00 | 10 |
| |
2017/08/29 | Jiayu Guo | 11:00 | 21:00 | 10 |
| |
2017/08/30 | Shipan Ren | 10:00 | 20:00 | 10 |
| |
2017/08/30 | Jiayu Guo | 11:30 | 21:00 | 9 |
| |
2017/08/31 | Shipan Ren | 10:00 | 20:00 | 10 |
| |
2017/08/31 | Jiayu Guo | 10:00 | 20:00 | 10 |
|
Date | Yang Feng | Jiyuan Zhang |
---|