“Hulan-2014-11-20”版本间的差异
来自cslt Wiki
（→Knowledge Online Learning） |
|||
| 第15行： | 第15行： | ||
* help duxk to rewrite the code. | * help duxk to rewrite the code. | ||
===Knowledge Online Learning=== | ===Knowledge Online Learning=== | ||
| − | * research the algorithm | + | * research the algorithm('''liurong''') |
| + | |||
==knowledge structure== | ==knowledge structure== | ||
* how to inference the knowledge. | * how to inference the knowledge. | ||
2014年11月20日 (四) 05:12的最后版本
目录
Dialog system
Algorithm
Spell mistake
- train a new lm (or mix the two lm)(caoli)
improve fuzzy match
- add Synonyms similarity using MERT-4 method
improve lucene search
- lucene Optimization(liurong)
- rewrite the method to select the 50 standard question not same template.(hold)
- using MERT-4 method to get good value of multi-feature.like IDF,NER,baidu_weight,keyword etc.(hold)
- MERT-4 method (caoli liurong)
- feature score: standard question,standard question and answer, standard question and extracted question,baixing-dict,sogou-weight.
Multi-Scene Recognition
- demo (done)
- help duxk to rewrite the code.
Knowledge Online Learning
- research the algorithm(liurong)
knowledge structure
- how to inference the knowledge.
Knowledge Management and labeling system
- continue coding.
Patent
- the GA method to improve QA .(liurong)
source from company
- baixiti-dict (duxk)
- history test set (duxk)
