From cslt Wiki
- 1 Speech Processing
- 1.1 AM development
- 1.2 Speaker ID
- 2 Text Processing
- 2.1 LM development
- 2.2 Word2Vector
- 2.3 Translation
- 2.4 Sparse NN in NLP
- 2.5 QA
- 2.6 online learning
- May gpu760 of grid-14 has been repairing.
- grid-11 often shutdown automatically, too slow computation speed.
- details at http://liuc.cslt.org/pages/rnnam.html
- XueWei is reading papers and preparing the technical report
Dropout & Maxout & rectifier
- Need to solve the too small learning-rate problem
- 20h small scale sparse dnn with rectifier. --Chao liu
- 20h small scale sparse dnn with Maxout/rectifier based on weight-magnitude-pruning. --Mengyuan Zhao
- Convolutive network(DAE)
- Technical report to draft, Mian Wang, Yiye Lin, Shi Yin, Mengyuan Zhao
- Technical report to draft, Xiangyu Zeng, Shi Yin, Mengyuan Zhao and Zhiyong Zhang,
RNN-DAE(Deep based Auto-Encode-RNN)
- Technical report -- Shi Yin
Speech rate training
- Technical report to draft. Xiangyu Zeng, Shi Yin
- Prepare for ChinaSIP
- Reproduce the experiments on fisher dataset.
- Use the fisher DNN model to decode all-wsj dataset
- preparing scoring for puqiang data
Neural network visulization
- Technical report, Mian Wang.
Domain specific LM
- mix the sougou2T-lm,kn-discount(done)
- train a large lm using 25w-dict.(hanzhenglong/wxx)
- v2.0a adjust the weight and smaller weight of transcription is better.(done)
- v2.0b add the v1.0 vocab(this week)
- v2.0c filter the useless word.(next week)
- set the test set for new word (hold)
- Tag Lm
- add 3-class tag and test
- similar word extension in FST
- improve the key-word weight in G , and result is good in keyword recognization
- read to deal with the English-Chinese
- test wer RNNLM on Chinese data from jietong-data
- generate the ngram model from rnnlm and test the ppl with different size txt.
- check the lstm-rnnlm code about how to Initialize and update learning rate.(hold)
W2V based doc classification
- data prepare.
- run the big data
- write the paper.
Character to word
- Character to word conversion(hold)
Word vector online learing
- prepare the ACL
- v5.0 demo released
- cut the dict and use new segment-tool
Sparse NN in NLP
- write a technical report(Wednesday) and make a report.
- ready to prepare the ACL
improve fuzzy match
- add Synonyms similarity using MERT-4 method(hold)
improve lucene search
- add more feature to improve search.
- POS, NER ,tf ,idf
- result:P@1: 0.68734335-->0.7763158P@5: 0.80325814-->0.8383459 
- Optimize the code about extracting features and reranking and commit to Rong Liu to check in.
- using sentence vector, it doesn't work.
- online learning to rank
- tool is ok and ready to test
- a simple edition about online learning part about QA.
- code for organization
- using NER to normalize the word
- new inter will install SEMPRE