“2014-11-25”版本间的差异
来自cslt Wiki
（→tag LM） |
（→Text Processing） |
||
| （3位用户的14个中间修订版本未显示） | |||
| 第4行： | 第4行： | ||
==== Environment ==== | ==== Environment ==== | ||
* Already buy 3 760GPU | * Already buy 3 760GPU | ||
| − | * grid-9 760GPU crashed again; | + | * grid-9 760GPU crashed again; |
| − | * | + | * Change 760gpu card of grid-12 and grid-14 |
| − | + | ||
==== Sparse DNN ==== | ==== Sparse DNN ==== | ||
* Performance improvement found when pruned slightly | * Performance improvement found when pruned slightly | ||
| − | * need retraining for unpruned one; training loss | + | * need retraining for unpruned one; training loss |
| − | + | ||
* details at http://liuc.cslt.org/pages/sparse.html | * details at http://liuc.cslt.org/pages/sparse.html | ||
| 第29行： | 第27行： | ||
* Drop out | * Drop out | ||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
:* AURORA4 dataset | :* AURORA4 dataset | ||
| − | + | :* Use different proportion of noise data to investigate the effect of xEnt and mpe and dropout | |
| − | + | :** Problem 1) The effect of dropout in different noise proportion; | |
| − | + | 2) The effect of MPE in different noise proportion; | |
| − | + | 3) The effect of MPE+dropout in different noise proportion. | |
| − | + | :**http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?step=view_request&cvssid=261 | |
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | :** Find and test unknown noise test-data.(++) | |
| − | + | ||
| − | :** Find and test unknown noise test-data.(+) | + | |
:** Have done the droptout on normal trained XEnt NNET , eg wsj(learn-rate:1e-4/1e-5). Seems small learn-rate get the balance of accuracy and train-time. | :** Have done the droptout on normal trained XEnt NNET , eg wsj(learn-rate:1e-4/1e-5). Seems small learn-rate get the balance of accuracy and train-time. | ||
| − | :** | + | :** Debug the low cv frame-accuracy |
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
* MaxOut | * MaxOut | ||
| 第93行： | 第43行： | ||
1) AURORA4 -15h | 1) AURORA4 -15h | ||
NOTE: gs==groupsize | NOTE: gs==groupsize | ||
| − | + | :* pretraining based maxout | |
| + | :** Select units in Groupsize interval, but need low learn-rate | ||
| + | :** Force accept the first iteration. Jump out from the local-minimum | ||
| + | |||
| + | * P-norm | ||
| + | --------------------------------------------------------------------------------------------------------- | ||
model/testcase(WER) | test_clean_wv1 | test_airport_wv1 | test_babble_wv1 | test_car_wv1 | model/testcase(WER) | test_clean_wv1 | test_airport_wv1 | test_babble_wv1 | test_car_wv1 | ||
--------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------- | ||
| − | + | nnet_std-baseline | 6.04 | 29.91 | 27.76 | 16.37 | |
--------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------- | ||
| − | + | lr0.008-1e-7_gs6_p2 | 6.17 | 27.51 | 24.98 | 15.40 | |
--------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------- | ||
| − | + | lr0.008-1e-7_gs10_p2 | 6.40 | 28.18 | 26.60 | 15.82 | |
--------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------- | ||
| − | + | lr0.008-1e-7_gs10_p3 | 6.45 | 28.73 | 30.01 | 20.24 | |
--------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------- | ||
| − | + | lr0.04-4e-3_gs6_p2 | 6.47 | 27.42 | 27.48 | 17.35 | |
--------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------- | ||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
* Convolutive network (+) | * Convolutive network (+) | ||
:* AURORA 4 | :* AURORA 4 | ||
| + | :** 1) | ||
| + | ----------------------------------------------------------------------------------------------------------------------- | ||
| wer | hid-layers | hid-dim | delta-order | splice | lda-dim | learn-rate | pooling | TBA | | wer | hid-layers | hid-dim | delta-order | splice | lda-dim | learn-rate | pooling | TBA | ||
----------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------- | ||
| 第156行： | 第80行： | ||
cnn_std_1200_3 | 6.66 | 5 | 1200 | 0 | 4 | 198 | 0.008 | 3 |patch-dim1 7 | cnn_std_1200_3 | 6.66 | 5 | 1200 | 0 | 4 | 198 | 0.008 | 3 |patch-dim1 7 | ||
----------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------- | ||
| + | :** 2) | ||
| + | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ||
| + | | %WER | Dnnhiddenlayers | hid-dim | pooling | CNN_unit |cnn_init_opts | ||
| + | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ||
| + | cnn_nonlda_std | 5.73 | 4 | 1200 | 3 | |"--patch-dim1 8" input_dim ~ patch-dim1 | ||
| + | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ||
| + | cnn_nonlda_cnnunit_384 | 5.85 | 4 | 1200 | 3 | 384 |"--patch-dim1 8 --num-filters2 384" | ||
| + | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ||
| + | cnn_nonlda_cnnunit_220 | ---------- | 4 | 1200 | 3 | 220 |"--patch-dim1 8 --num-filters2 220" | ||
| + | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ||
| − | + | ====MSE==== | |
| + | (1) AURORA4 (train_clean) | ||
| + | drop-retention/testcase(WER) | test_clean_wv1 | test_airport_wv1 | test_babble_wv1 | test_car_wv1 | ||
| + | --------------------------------------------------------------------------------------------------------- | ||
| + | std-baseline_xent | 6.04 | 29.91 | 27.76 | 16.37 | ||
| + | --------------------------------------------------------------------------------------------------------- | ||
| + | std-baseline_mse | 6.05 | 31.30 | 30.03 | 15.77 | ||
| + | --------------------------------------------------------------------------------------------------------- | ||
| + | |||
| + | ====DAE(Deep Atuo-Encode)==== | ||
| + | (1) train_clean | ||
| + | drop-retention/testcase(WER)| test_clean_wv1 | test_airport_wv1 | test_babble_wv1 | test_car_wv1 | ||
| + | --------------------------------------------------------------------------------------------------------- | ||
| + | std-xEnt-sigmoid-baseline| 6.04 | 29.91 | 27.76 | 16.37 | ||
| + | --------------------------------------------------------------------------------------------------------- | ||
| + | std+dae_cmvn_noFT_2-1200 | 7.10 | 15.33 | 16.58 | 9.23 | ||
| + | --------------------------------------------------------------------------------------------------------- | ||
| + | std+dae_cmvn_splice5_2-100 | 8.19 | 15.21 | 15.25 | 9.31 | ||
| + | --------------------------------------------------------------------------------------------------------- | ||
====Denoising & Farfield ASR==== | ====Denoising & Farfield ASR==== | ||
| 第165行： | 第117行： | ||
====VAD==== | ====VAD==== | ||
* Frame energy feature extraction, done | * Frame energy feature extraction, done | ||
| − | * Harmonics and Teager energy features being investigation | + | * Harmonics and Teager energy features being investigation (+) |
| − | * Previous results to be organized for a paper | + | * Previous results to be organized for a paper |
| + | * MPE model VAD test | ||
====Speech rate training==== | ====Speech rate training==== | ||
| − | * Data ready on tencent set; some errors on speech rate dependent model | + | * Data ready on tencent set; some errors on speech rate dependent model |
| − | * Retrain new model | + | * Retrain new model(+) |
====Scoring==== | ====Scoring==== | ||
| 第176行： | 第129行： | ||
* harmonics based timber comparison: frequency based feature is better | * harmonics based timber comparison: frequency based feature is better | ||
* GMM based timber comparison is done. Similar to speaker recognition | * GMM based timber comparison is done. Similar to speaker recognition | ||
| − | * TODO: Code checkin and technique report | + | * TODO: Code checkin and '''technique report''' |
====Confidence==== | ====Confidence==== | ||
| 第185行： | 第138行： | ||
===Speaker ID=== | ===Speaker ID=== | ||
* Preparing GMM-based server. | * Preparing GMM-based server. | ||
| − | * EER ~ | + | * EER ~ 4% (GMM-based system)--Text independent |
| + | * EER ~ 6%(1s) / 0.5%(5s) (GMM-based system)--Text dependent | ||
* test different number of components; fast i-vector computing | * test different number of components; fast i-vector computing | ||
| 第191行： | 第145行： | ||
* GMM-based language is ready. | * GMM-based language is ready. | ||
* Delivered to Jietong | * Delivered to Jietong | ||
| + | * Prepare the test-case | ||
| − | === | + | ===Voice Conversion=== |
| − | + | * Yiye is reading materials | |
| − | * | + | |
| 第211行： | 第165行： | ||
====tag LM==== | ====tag LM==== | ||
| − | * different weight | + | * different weight [http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=lr&step=view_request&cvssid=304 2014-Nov-23,Monday] |
:* | :* | ||
{| border="2px" | {| border="2px" | ||
| 第280行： | 第234行： | ||
|- | |- | ||
|} | |} | ||
| − | :* | + | :* conclusion: |
| − | + | ||
1. compare experiment 3 with experiment 5: | 1. compare experiment 3 with experiment 5: | ||
same jsgf file, but the tag number in corpus if different, we can find that when add | same jsgf file, but the tag number in corpus if different, we can find that when add | ||
| 第288行： | 第241行： | ||
same tag number in corpus, but different jsgf size, we can find that different jsgf size have the | same tag number in corpus, but different jsgf size, we can find that different jsgf size have the | ||
same optimal weight. | same optimal weight. | ||
| − | |||
| − | |||
| − | |||
* need to do | * need to do | ||
| − | :* | + | :* tag Probability should test add the weight(hanzhenglong) and handover to hanzhenglong ('''this week''') |
| − | + | :* make a summary about tag-lm and '''journal paper'''(wxx and yuanb)('''two weeks'''). | |
| − | :* make a summary about tag-lm . | + | |
====RNN LM==== | ====RNN LM==== | ||
*rnn | *rnn | ||
| − | :* test RNNLM on Chinese data from jietong-data | + | :* test wer RNNLM on Chinese data from jietong-data('''this week''') |
:* check the rnnlm code about how to Initialize and update learning rate. | :* check the rnnlm code about how to Initialize and update learning rate. | ||
| + | :* generate the ngram model from rnnlm and test the ppl with different size txt.('''this week''') | ||
*lstm+rnn | *lstm+rnn | ||
:* check the lstm-rnnlm code about how to Initialize and update learning rate. | :* check the lstm-rnnlm code about how to Initialize and update learning rate. | ||
| 第307行： | 第257行： | ||
====W2V based doc classification==== | ====W2V based doc classification==== | ||
| − | * Initial results variable Bayesian GMM obtained. Performance is not as good as the conventional GMM. | + | * Initial results variable Bayesian GMM obtained. Performance is not as good as the conventional GMM.(hold) |
* Non-linear inter-language transform: English-Spanish-Czch: wv model training done, transform model on investigation | * Non-linear inter-language transform: English-Spanish-Czch: wv model training done, transform model on investigation | ||
| − | + | ====Knowledge vector==== | |
| − | + | ||
| − | + | ||
* Knowledge vector started | * Knowledge vector started | ||
| − | :* | + | :* begin to code |
| − | + | ====Character to wordr==== | |
| − | * Character to word conversion | + | * Character to word conversion(hold) |
:* prepare the task: word similarity | :* prepare the task: word similarity | ||
:* prepare the dict. | :* prepare the dict. | ||
| 第321行： | 第269行： | ||
===Translation=== | ===Translation=== | ||
| − | * | + | * v5.0 demo released |
:* cut the dict and use new segment-tool | :* cut the dict and use new segment-tool | ||
| 第328行： | 第276行： | ||
====Spell mistake==== | ====Spell mistake==== | ||
* retrain the ngram model('''caoli''') | * retrain the ngram model('''caoli''') | ||
| − | |||
| − | |||
| − | |||
====improve fuzzy match==== | ====improve fuzzy match==== | ||
* add Synonyms similarity using MERT-4 method(hold) | * add Synonyms similarity using MERT-4 method(hold) | ||
| − | |||
====improve lucene search==== | ====improve lucene search==== | ||
:* using MERT-4 method to get good value of multi-feature.like IDF,NER,baidu_weight,keyword etc.('''liurong this month''') | :* using MERT-4 method to get good value of multi-feature.like IDF,NER,baidu_weight,keyword etc.('''liurong this month''') | ||
| − | |||
====Multi-Scene Recognition==== | ====Multi-Scene Recognition==== | ||
| − | * | + | * handover to duxk('''this week''') |
| − | + | ====XiaoI framework==== | |
| − | + | * give a report about xiaoI framework | |
* new inter will install SEMPRE | * new inter will install SEMPRE | ||
| + | ====patent==== | ||
| + | * GA-method improve the QA('''this week''') | ||
2014年12月8日 (一) 02:00的最后版本
目录
[隐藏]Speech Processing
AM development
Environment
- Already buy 3 760GPU
- grid-9 760GPU crashed again;
- Change 760gpu card of grid-12 and grid-14
Sparse DNN
- Performance improvement found when pruned slightly
- need retraining for unpruned one; training loss
- details at http://liuc.cslt.org/pages/sparse.html
RNN AM
- Initial nnet seems not very well, need to be pre-trained or test lower learn-rate.
- For AURORA 4 1h/epoch, model train done.
- Using AURORA 4 short-sentence with a smaller number of targets.(+)
- Adjusting the learning rate.(+)
- Trying toolkit of Microsoft.(+)
- details at http://liuc.cslt.org/pages/rnn.html
A new nnet training scheduler
- Initial code done. No better than original one considering of taking much more iterations.
- details at http://liuc.cslt.org/pages/nnet-sched.html
Drop out & Rectification & convolutive network
- Drop out
- AURORA4 dataset
- Use different proportion of noise data to investigate the effect of xEnt and mpe and dropout
- Problem 1) The effect of dropout in different noise proportion;
- Use different proportion of noise data to investigate the effect of xEnt and mpe and dropout
2) The effect of MPE in different noise proportion;
3) The effect of MPE+dropout in different noise proportion.
- Find and test unknown noise test-data.(++)
- Have done the droptout on normal trained XEnt NNET , eg wsj(learn-rate:1e-4/1e-5). Seems small learn-rate get the balance of accuracy and train-time.
- Debug the low cv frame-accuracy
- MaxOut
- 6min/epoch
1) AURORA4 -15h NOTE: gs==groupsize
- pretraining based maxout
- Select units in Groupsize interval, but need low learn-rate
- Force accept the first iteration. Jump out from the local-minimum
- pretraining based maxout
- P-norm
---------------------------------------------------------------------------------------------------------
model/testcase(WER) | test_clean_wv1 | test_airport_wv1 | test_babble_wv1 | test_car_wv1
---------------------------------------------------------------------------------------------------------
nnet_std-baseline | 6.04 | 29.91 | 27.76 | 16.37
---------------------------------------------------------------------------------------------------------
lr0.008-1e-7_gs6_p2 | 6.17 | 27.51 | 24.98 | 15.40
---------------------------------------------------------------------------------------------------------
lr0.008-1e-7_gs10_p2 | 6.40 | 28.18 | 26.60 | 15.82
---------------------------------------------------------------------------------------------------------
lr0.008-1e-7_gs10_p3 | 6.45 | 28.73 | 30.01 | 20.24
---------------------------------------------------------------------------------------------------------
lr0.04-4e-3_gs6_p2 | 6.47 | 27.42 | 27.48 | 17.35
---------------------------------------------------------------------------------------------------------
- Convolutive network (+)
- AURORA 4
:** 1)
-----------------------------------------------------------------------------------------------------------------------
| wer | hid-layers | hid-dim | delta-order | splice | lda-dim | learn-rate | pooling | TBA
-----------------------------------------------------------------------------------------------------------------------
cnn_std_baseline| 6.70 | 4 | 1200 | 0 | 4 | 198 | 0.008 | 3 |patch-dim1 7
-----------------------------------------------------------------------------------------------------------------------
cnn_std_1000_3 | 6.61 | 4 | 1000 | 0 | 4 | 198 | 0.008 | 3 |patch-dim1 7
-----------------------------------------------------------------------------------------------------------------------
cnn_std_1400_3 | 6.61 | 4 | 1400 | 0 | 4 | 198 | 0.008 | 3 |patch-dim1 7
-----------------------------------------------------------------------------------------------------------------------
cnn_std_1200_4 | 6.91 | 4 | 1200 | 0 | 4 | 198 | 0.008 | 4 |patch-dim1 6
-----------------------------------------------------------------------------------------------------------------------
cnn_std_1200_2 | - | 4 | 1200 | 0 | 4 | 198 | 0.008 | 2 |patch-dim1 8
-----------------------------------------------------------------------------------------------------------------------
cnn_std_1200_3 | 6.66 | 5 | 1200 | 0 | 4 | 198 | 0.008 | 3 |patch-dim1 7
-----------------------------------------------------------------------------------------------------------------------
:** 2)
----------------------------------------------------------------------------------------------------------------------------------------------------------------------------
| %WER | Dnnhiddenlayers | hid-dim | pooling | CNN_unit |cnn_init_opts
----------------------------------------------------------------------------------------------------------------------------------------------------------------------------
cnn_nonlda_std | 5.73 | 4 | 1200 | 3 | |"--patch-dim1 8" input_dim ~ patch-dim1
----------------------------------------------------------------------------------------------------------------------------------------------------------------------------
cnn_nonlda_cnnunit_384 | 5.85 | 4 | 1200 | 3 | 384 |"--patch-dim1 8 --num-filters2 384"
----------------------------------------------------------------------------------------------------------------------------------------------------------------------------
cnn_nonlda_cnnunit_220 | ---------- | 4 | 1200 | 3 | 220 |"--patch-dim1 8 --num-filters2 220"
----------------------------------------------------------------------------------------------------------------------------------------------------------------------------
MSE
(1) AURORA4 (train_clean)
drop-retention/testcase(WER) | test_clean_wv1 | test_airport_wv1 | test_babble_wv1 | test_car_wv1
---------------------------------------------------------------------------------------------------------
std-baseline_xent | 6.04 | 29.91 | 27.76 | 16.37
---------------------------------------------------------------------------------------------------------
std-baseline_mse | 6.05 | 31.30 | 30.03 | 15.77
---------------------------------------------------------------------------------------------------------
DAE(Deep Atuo-Encode)
(1) train_clean
drop-retention/testcase(WER)| test_clean_wv1 | test_airport_wv1 | test_babble_wv1 | test_car_wv1
---------------------------------------------------------------------------------------------------------
std-xEnt-sigmoid-baseline| 6.04 | 29.91 | 27.76 | 16.37
---------------------------------------------------------------------------------------------------------
std+dae_cmvn_noFT_2-1200 | 7.10 | 15.33 | 16.58 | 9.23
---------------------------------------------------------------------------------------------------------
std+dae_cmvn_splice5_2-100 | 8.19 | 15.21 | 15.25 | 9.31
---------------------------------------------------------------------------------------------------------
Denoising & Farfield ASR
- ICASSP paper submitted.
- HOLD
VAD
- Frame energy feature extraction, done
- Harmonics and Teager energy features being investigation (+)
- Previous results to be organized for a paper
- MPE model VAD test
Speech rate training
- Data ready on tencent set; some errors on speech rate dependent model
- Retrain new model(+)
Scoring
- Timber Comparison done.
- harmonics based timber comparison: frequency based feature is better
- GMM based timber comparison is done. Similar to speaker recognition
- TODO: Code checkin and technique report
Confidence
- Reproduce the experiments on fisher dataset.
- Use the fisher DNN model to decode all-wsj dataset
- preparing scoring for puqiang data
Speaker ID
- Preparing GMM-based server.
- EER ~ 4% (GMM-based system)--Text independent
- EER ~ 6%(1s) / 0.5%(5s) (GMM-based system)--Text dependent
- test different number of components; fast i-vector computing
Language ID
- GMM-based language is ready.
- Delivered to Jietong
- Prepare the test-case
Voice Conversion
- Yiye is reading materials
Text Processing
LM development
Domain specific LM
- domain lm(need to discuss with xiaoxi)
- embedded language model(this week)
- train some more LMs with Zhenlong (dianzishu sogou bbs chosen)("need result").
- keep on training sogou2T lm(14/16 on 3rd iteration).(this week)
- new dict.
- handover of this work to hanzhenglong, give a simple docuemnt(this week)
tag LM
- different weight 2014-Nov-23,Monday
| method | tag-jsgf | corpus | weight | wer | ser | add_wer |
|---|---|---|---|---|---|---|
| experiment 3 | 500(490 less frequent and 10 unseen) | 500 | 0.1 | 16.72 | 77.92 | - |
| 0.3 | 15.42 | 71.25 | - | |||
| 0.5 | 15.40 | 69.58 | - | |||
| 0.7 | 15.28 | 68.75 | - | |||
| 0.8 | 15.38 | 68.33 | - | |||
| 1 | 15.98 | 69.17 | - | |||
| 2 | 19.08 | 70.83 | - | |||
| experiment 4 | 100(90 less frequent and 10 unseen) | 100 | 0.008 | 15.28 | 69.58 | - |
| 0.02 | 14.84 | 69.58 | - | |||
| 0.05 | 15.11 | 69.58 | - | |||
| 0.1 | 15.30 | 69.75 | - | |||
| 0.3 | 16.01 | 70.42 | - | |||
| experiment 5 | 500 | 100 | 0.01 | 17.57 | 78.75 | - |
| 0.05 | 16.84 | 77.08 | - | |||
| 0.08 | 16.59 | 76.25 | - | |||
| 0.15 | 16.76 | 75.42 | - | |||
| experiment 6 | 1280 | 500 | 0.1 | 17.42 | 77.92 | - |
| 0.5 | 15.20 | 69.17 | - | |||
| 0.8 | 15.30 | 68.33 | - | |||
| 1 | 15.69 | 69.58 | - |
- conclusion:
1. compare experiment 3 with experiment 5: same jsgf file, but the tag number in corpus if different, we can find that when add more tag to corpus, the optimal weight is larger. 2. compare experiment 3 with experiment 6: same tag number in corpus, but different jsgf size, we can find that different jsgf size have the same optimal weight.
- need to do
- tag Probability should test add the weight(hanzhenglong) and handover to hanzhenglong (this week)
- make a summary about tag-lm and journal paper(wxx and yuanb)(two weeks).
RNN LM
- rnn
- test wer RNNLM on Chinese data from jietong-data(this week)
- check the rnnlm code about how to Initialize and update learning rate.
- generate the ngram model from rnnlm and test the ppl with different size txt.(this week)
- lstm+rnn
- check the lstm-rnnlm code about how to Initialize and update learning rate.
Word2Vector
W2V based doc classification
- Initial results variable Bayesian GMM obtained. Performance is not as good as the conventional GMM.(hold)
- Non-linear inter-language transform: English-Spanish-Czch: wv model training done, transform model on investigation
Knowledge vector
- Knowledge vector started
- begin to code
Character to wordr
- Character to word conversion(hold)
- prepare the task: word similarity
- prepare the dict.
Translation
- v5.0 demo released
- cut the dict and use new segment-tool
QA
deatil:[1]
Spell mistake
- retrain the ngram model(caoli)
improve fuzzy match
- add Synonyms similarity using MERT-4 method(hold)
improve lucene search
- using MERT-4 method to get good value of multi-feature.like IDF,NER,baidu_weight,keyword etc.(liurong this month)
Multi-Scene Recognition
- handover to duxk(this week)
XiaoI framework
- give a report about xiaoI framework
- new inter will install SEMPRE
patent
- GA-method improve the QA(this week)
