Difference between revisions of "NLP Status Report 2017-5-22"

From cslt Wiki
Jump to: navigation, search
(以“{| class="wikitable" !Date !! People !! Last Week !! This Week |- | rowspan="6"|2017/4/5 |Jiyuan Zhang || || |- |Aodong LI || || |- |Shiyue Zhang || * tried to no...”为内容创建页面)
 
Line 19: Line 19:
 
|-
 
|-
 
|Shipan Ren ||
 
|Shipan Ren ||
* configured environment and ran tf_translate code
+
 
* read machine translation paper
+
* learned lstm model and seq2seq model
+
 
||
 
||
* learn the implement of seq2seq model
+
 
* read tf_translate code
+
* understand the meaning of main code
+
 
|}
 
|}

Revision as of 03:29, 22 May 2017

Date People Last Week This Week
2017/4/5 Jiyuan Zhang
Aodong LI
Shiyue Zhang
  • tried to not train embedding but use external word vectors
  • most results of my attempts are bad, only 3-layer rnn + no dropout model got 25.54 bleu which about 2 points worse than original baseline
  • trained original baseline on new data ( the data fixed the reverse sentence problem), got bleu=27.88; moses bleu=32.47
  • try more models to get similar results as original baseline on new data
  • m-nmt model on new data
Shipan Ren