Date |
Person |
start |
leave |
hours |
status
|
2016/09/01
|
Aodong Li |
|
|
|
|
Ziwei Bai |
|
|
|
|
Andy Zhang |
9:30 |
18:00 |
7.5 |
read papers about neural turing machine & memory networks
|
Shiyao Li |
11:40 |
18:00 |
5 |
learn word2vec using tensorflow
|
2016/09/02
|
Aodong Li |
|
|
|
|
Ziwei Bai |
|
|
|
|
Andy Zhang |
9:30 |
18:30 |
8 |
continued reading papers got yesterday, mainly focus on the implementation of the models.
|
Shiyao Li |
9:30 |
18:30 |
8 |
learn LSTM using tensorflow and get to know some applications about generating text and sequence
|
2016/09/05
|
Aodong Li |
12:50 |
20:00 |
7 |
Reconsider the rare word mechanism and do some experiments to try to reproduce the paper's method
|
Ziwei Bai |
|
|
|
|
Andy Zhang |
|
|
|
|
Shiyao Li |
|
|
|
|
2016/09/06
|
Aodong Li |
15:40 |
19:50 |
5 |
- Do the baseline experiment but the performance is poor, so I may conduct it wrong
- Help Lantian for ICASSP with codes
|
Ziwei Bai |
|
|
|
|
Andy Zhang |
|
|
|
|
Shiyao Li |
|
|
|
|
Shiyue Zhang |
14:30 |
20:00 |
5 |
- Getting familiar with ASR engine and prepare for the document
|
2016/09/07
|
Aodong Li |
14:10 |
20:50 |
6.5 |
- Try different settings for rare word baseline experiment but still got wrong performance
- Read the paper "Pointing the unknown words"
|
Ziwei Bai |
|
|
|
|
Andy Zhang |
|
|
|
|
Shiyao Li |
|
|
|
|
Shiyue Zhang |
9:30 |
19:30 |
8.5 |
- Read ASR code and write the document
|
2016/09/08
|
Aodong Li |
|
|
|
|
Ziwei Bai |
|
|
|
|
Andy Zhang |
|
|
|
|
Shiyao Li |
|
|
|
|
Shiyue Zhang |
9:30 |
16:30 |
5 |
- Read the paper "Neural Machine Translation By Jointly Learning"
|
2016/09/09
|
Aodong Li |
|
|
|
|
Ziwei Bai |
|
|
|
|
Andy Zhang |
|
|
|
|
Shiyao Li |
|
|
|
|
Shiyue Zhang |
14:00 |
19:30 |
5 |
- Read the paper "Memory Networks" and finish the document
|
2016/09/10
|
Aodong Li |
|
|
|
|
Ziwei Bai |
11:00 |
20:00 |
8 |
test the chatting model 60-160
|
Andy Zhang |
|
|
|
|
Shiyao Li |
|
|
|
|
Shiyue Zhang |
|
|
|
|
2016/09/12
|
Aodong Li |
|
|
|
|
Ziwei Bai |
9:15 |
18:15 |
8 |
prepare for the slide for Chatting Model(CDSSM & NRM)
|
Andy Zhang |
9:15 |
18:30 |
8+ |
prepared for the paper sharing
|
Shiyao Li |
9:15 |
18:15 |
8 |
read the paper Finding the Middle Ground-A Model for Planning Satisficing Answers
|
Shiyue Zhang |
9:00 |
20:00 |
9.5 |
- Review the two papers I've read last week and ask questions
- Read the paper "Recurrent Neural Network Grammars"
|
2016/09/13
|
Aodong Li |
|
|
|
|
Ziwei Bai |
9:20 |
18:20 |
8 |
- install scrapy & beautifulSoup
- learn scrapy
|
Andy Zhang |
9:20 |
18:20 |
8 |
- continue preparing for the paper sharing
- set up env for MemN2N code lua version(for language model)
|
Shiyao Li |
|
|
|
|
Shiyue Zhang |
9:00 |
17:30 |
7.5 |
- Review the paper "Recurrent Neural Network Grammars" and ask questions
- Try to run the code of RNNG
|
2016/09/14
|
Aodong Li |
|
|
|
|
Ziwei Bai |
9:20 |
18:00 |
7+ |
try using scrapy download company public announcement from sina(170MB)
|
Andy Zhang |
9:20 |
18:20 |
8 |
- tried to finish running the source code of MemN2N but it crashed
- tried to install torch on the server without root but failed
- will finish running the source code at home
|
Shiyao Li |
9:20 |
6:20 |
8 |
- finish the ppt for paper sharing and pre-share it with Leader Feng
|
Shiyue Zhang |
|
|
|
|
2016/09/15
|
Aodong Li |
|
|
|
|
Ziwei Bai |
10:30 |
20:00 |
8.5 |
- try using scrapy download 'data learn' and 'blog' from sina(115MB)
- realize renew automatically everyday
|
Andy Zhang |
|
|
|
|
Shiyao Li |
|
|
|
|
Shiyue Zhang |
|
|
|
|
2016/09/17
|
Aodong Li |
|
|
|
|
Ziwei Bai |
|
|
|
|
Andy Zhang |
|
|
|
|
Shiyao Li |
|
|
|
|
Shiyue Zhang |
10:00 |
20:00 |
9 |
- help Lantian, Wangyang and Zhiyuan to check papers
|
2016/09/18
|
Aodong Li |
|
|
|
|
Ziwei Bai |
9:30 |
18:30 |
8 |
- try using scrapy download 'Wall news' & 'zqsb'(400M)
|
Andy Zhang |
9:30 |
18:30 |
8 |
- reviewed paper that is to be shared tomorrow
- tried to set the env for a c++ code but failed
|
Shiyao Li |
9:30 |
6:30 |
8 |
- review the non-parametric model written by Maoning Wang and learn about Latex
- help Wangyang check his paper's language problems
|
Shiyue Zhang |
14:30 |
20:00 |
5 |
- help Wang Yang and Tang Zhiyuan to check papers
- try to understand and run the code of RNNG
|
2016/09/19
|
Aodong Li |
|
|
|
|
Ziwei Bai |
9:20 |
18:30 |
8 |
- continue download news(2G)
|
Andy Zhang |
9:20 |
18:30 |
8 |
- set the env for rnng code
- shared a paper
|
Shiyao Li |
9:20 |
18:30 |
8 |
- share a paper
- keep understanding what Maoning Wang has written about Chapter 8
|
Shiyue Zhang |
9:00 |
19:30 |
9 |
- Try to compile the rnng code, ask Zhiyong for help
|
2016/09/20
|
Aodong Li |
|
|
|
|
Ziwei Bai |
9:10 |
15:40 |
5.5 |
|
Andy Zhang |
9:10 |
18:10 |
8 |
- continue work on the env setting of rnng, had small progress, aborted it
- find several open sources of NTM
- read the source code of MemN2N in lua(torch)
|
Shiyao Li |
|
|
|
|
Shiyue Zhang |
14:00 |
19:30 |
5.5 |
- Compile the code successfully
- Try to run the code
|
2016/09/21
|
Aodong Li |
|
|
|
|
Ziwei Bai |
13:00 |
22:00 |
8 |
- spider QA(failed in zhihu)
|
Andy Zhang |
9:10 |
12:20 |
3 |
- read the code of MemN2N in lua(torch)
|
Shiyao Li |
|
|
|
|
Shiyue Zhang |
9:30 |
19:30 |
8.5 |
- Run the code sucessfully using a fragment of data
- Try to format the whole dataset
|
2016/09/22
|
Aodong Li |
|
|
|
|
Ziwei Bai |
10:20 |
22:20 |
11 |
|
Andy Zhang |
9:30 |
18:30 |
8 |
read source code of end2end memory network
|
Shiyao Li |
|
|
|
|
Shiyue Zhang |
9:20 |
20:20 |
9 |
- format the full version of data
- debug the discriminative model code
|
2016/09/23
|
Aodong Li |
|
|
|
|
Ziwei Bai |
9:30 |
23:30 |
13 |
- program script to test the chatting model
- spider QA from tianya (unsolved question)
- spider QA from zhihu.sogou.com(still run, but slow)
- filter the deteset for word vector
|
Andy Zhang |
9:20 |
18:20 |
8 |
- managed to understand the source code
|
Shiyao Li |
|
|
|
|
Shiyue Zhang |
14:30 |
20:00 |
5.5 |
- run discriminative model, find there is one step missing, and ask author for missing code
- run generative model successfully, but need to run again on newly formated data
- reformat the data, stemming the nonterminal tokens
|
2016/09/24
|
Aodong Li |
|
|
|
|
Ziwei Bai |
12:30 |
20:30 |
7 |
|
Andy Zhang |
|
|
|
|
Shiyao Li |
|
|
|
|
Shiyue Zhang |
|
|
|
|
2016/09/25
|
Aodong Li |
|
|
|
|
Ziwei Bai |
|
|
|
|
Andy Zhang |
|
|
|
|
Shiyao Li |
|
|
|
|
Shiyue Zhang |
13:30 |
20:30 |
6 |
- run the two models of rnng successfully
|
2016/09/26
|
Aodong Li |
|
|
|
|
Ziwei Bai |
9:30 |
22:30 |
12 |
*spider news
|
Andy Zhang |
10:00 |
20:00 |
9 |
- continued working on the source code
- ran memn2n several times, got a better result(closer to that in the paper)
|
Shiyao Li |
|
|
|
|
Shiyue Zhang |
9:30 |
19:00 |
8.5 |
- get the perfromance results of rnng, which agree with the original paper
- try to calculate the F1 score of generative model
|
2016/09/27
|
Aodong Li |
|
|
|
|
Ziwei Bai |
9:40 |
21:40 |
11 |
*spider news
|
Andy Zhang |
|
|
|
|
Shiyao Li |
|
|
|
|
Shiyue Zhang |
14:10 |
20:10 |
5 |
- get the mid states of discriminative model for memory network use
|